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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating research methodology and findings

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

    start of phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Selfer
    -0.45
     sp
    -0.39
     otherwise
    -0.39
    bootstrapcdn
    -0.38
     oth
    -0.37
     Otherwise
    -0.37
     hal
    -0.36
    Checks
    -0.36
     Suz
    -0.36
     checks
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.73
    LookAnd
    0.58
    ValueStyle
    0.57
    AddTagHelper
    0.57
     CreateTagHelper
    0.56
     Inscrivez
    0.54
    xase
    0.52
    OGND
    0.50
     nahilalakip
    0.48
     mijne
    0.47
    Act Density 0.072%

    No Known Activations