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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "catch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ddy
    -0.15
    Ń
    -0.15
     prox
    -0.14
    ramid
    -0.14
    artz
    -0.14
    irs
    -0.14
    HING
    -0.13
    ITA
    -0.13
    yi
    -0.13
     Ret
    -0.13
    POSITIVE LOGITS
    cha
    0.17
    asaki
    0.16
    chas
    0.15
     caught
    0.15
    late
    0.15
    /mit
    0.14
     Dangerous
    0.14
     catching
    0.14
    esModule
    0.14
    {}{↵
    0.14
    Act Density 0.023%

    No Known Activations