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

    Neuronpedia

    INDEX
    Explanations

    words related to occurrences or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "occur" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    step
    -0.87
    ilts
    -0.74
    iled
    -0.74
    edged
    -0.72
    ebus
    -0.70
    hub
    -0.68
    grown
    -0.68
    axter
    -0.68
    ilers
    -0.68
    shaw
    -0.67
    POSITIVE LOGITS
    uate
    1.06
    rences
    1.05
    uated
    0.91
    uates
    0.87
    uating
    0.87
    âĹ¼
    0.78
    uation
    0.78
    cffffcc
    0.77
     [&
    0.74
     anew
    0.73
    Act Density 0.029%

    No Known Activations