Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentiments and attitudes, particularly those related to cynicism, bias, and interpersonal feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Attitude" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    attitude towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.79
    NameInMap
    -0.74
    InvalidProtocol
    -0.71
    FormTagHelper
    -0.66
    tagHelperRunner
    -0.65
     EClass
    -0.63
    ///</
    -0.63
    ctest
    -0.62
     ligiloj
    -0.61
    parsedMessage
    -0.61
    POSITIVE LOGITS
     towards
    2.51
     toward
    2.44
    towards
    2.32
    toward
    2.23
     Towards
    2.12
     Toward
    2.00
    Towards
    1.91
    Toward
    1.80
     hacia
    1.71
     envers
    1.61
    Act Density 0.378%

    No Known Activations