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

    Neuronpedia

    INDEX
    Explanations

    detailed actions or processes involving multiple steps

    oai_token-act-pair · gpt-3.5-turbo

    instances of political alliances and divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Operation
    -0.57
    uthor
    -0.56
    issance
    -0.52
     Procedure
    -0.52
    TION
    -0.52
    PDATE
    -0.51
    ploy
    -0.50
    SW
    -0.49
    ħĭ
    -0.48
    vious
    -0.47
    POSITIVE LOGITS
     nowadays
    0.59
    vec
    0.58
     sqor
    0.56
     differently
    0.55
     yearly
    0.54
     fond
    0.54
    animate
    0.53
     everyday
    0.51
     regularly
    0.51
     theirs
    0.50
    Act Density 1.637%

    No Known Activations