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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" indicating temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.56
    Itoa
    -0.49
    Jereo
    -0.44
    RTEE
    -0.41
    Geplaatst
    -0.39
    NameInMap
    -0.39
     poffe
    -0.37
     linkovi
    -0.36
    rboles
    -0.36
    RefreshLayout
    -0.36
    POSITIVE LOGITS
     asked
    0.84
     compared
    0.84
     confronted
    0.79
     faced
    0.77
     discussing
    0.77
     considering
    0.77
     talking
    0.69
    compared
    0.69
     queried
    0.69
     dealing
    0.68
    Act Density 0.133%

    No Known Activations