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

    Neuronpedia

    INDEX
    Explanations

    acts of kindness or polite behavior

    oai_token-act-pair · gpt-3.5-turbo

    contexts involving physical items or actions related to development or accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.76
    ogether
    -0.68
    ierrez
    -0.68
    âķIJ
    -0.68
     exting
    -0.67
     UNCLASSIFIED
    -0.66
     looph
    -0.66
     millenn
    -0.63
    apego
    -0.63
     Azerb
    -0.62
    POSITIVE LOGITS
     âĢº
    0.84
    ↵Âł
    0.80
     âĢİ
    0.71
     ....
    0.67
     Belfast
    0.65
     Anime
    0.65
     ðŁĺ
    0.63
    Contents
    0.61
     spoilers
    0.61
     Posted
    0.60
    Act Density 2.390%

    No Known Activations