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

    Neuronpedia

    INDEX
    Explanations

    conditional statements expressing hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ábado
    -0.15
    idon
    -0.15
    $$$$
    -0.15
    .hxx
    -0.15
    don
    -0.14
    onder
    -0.14
    icon
    -0.14
    anken
    -0.13
    bread
    -0.13
    asaki
    -0.13
    POSITIVE LOGITS
    nt
    0.41
     be
    0.36
    ’ve
    0.29
    -be
    0.29
    've
    0.29
    /c
    0.26
    /is
    0.24
    NT
    0.23
     not
    0.22
     likely
    0.21
    Act Density 0.137%

    No Known Activations