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

    Neuronpedia

    INDEX
    Explanations

    references to decisions or actions made by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "move" indicating actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.79
    omial
    -0.75
    english
    -0.67
     Koran
    -0.63
    sung
    -0.61
    etheless
    -0.60
    inges
    -0.59
     risen
    -0.59
    oola
    -0.58
    icum
    -0.57
    POSITIVE LOGITS
    backs
    0.83
    ments
    0.82
    able
    0.82
    over
    0.81
    ment
    0.81
     toward
    0.77
    overs
    0.76
     towards
    0.76
    brates
    0.76
    rers
    0.73
    Act Density 0.031%

    No Known Activations