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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating hypothetical situations and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    álo
    -0.17
    ussen
    -0.17
    uniacid
    -0.15
    ideo
    -0.14
    actionDate
    -0.14
    instr
    -0.14
    ær
    -0.14
    ako
    -0.14
    ahir
    -0.14
    idis
    -0.14
    POSITIVE LOGITS
    iams
    0.20
    nt
    0.19
     be
    0.18
    've
    0.16
    URRENT
    0.15
    iam
    0.15
    -be
    0.15
    ’ve
    0.15
    t
    0.14
    167
    0.14
    Act Density 0.165%

    No Known Activations