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

    Neuronpedia

    INDEX
    Explanations

    words related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    words related to transformation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unts
    -0.69
    REL
    -0.66
    PLIED
    -0.66
    bis
    -0.65
    endment
    -0.63
     Reasons
    -0.63
    avering
    -0.62
    Found
    -0.61
     WARN
    -0.60
    draw
    -0.59
    POSITIVE LOGITS
    ively
    1.05
     into
    1.03
     INTO
    0.94
    into
    0.93
    ives
    0.86
    atted
    0.81
    ational
    0.79
     Into
    0.78
    ELF
    0.72
    oso
    0.71
    Act Density 0.052%

    No Known Activations