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

    Neuronpedia

    INDEX
    Explanations

    words related to actions of change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    words related to changing laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosyn
    -0.85
    ngth
    -0.81
    enegger
    -0.71
    ebus
    -0.70
     IMAGES
    -0.68
    swick
    -0.67
     Tone
    -0.66
    Hack
    -0.64
    OSH
    -0.64
     Wan
    -0.63
    POSITIVE LOGITS
    ment
    0.82
    atorium
    0.78
     moratorium
    0.76
    hee
    0.74
     grace
    0.72
    statement
    0.71
     euth
    0.70
    rarily
    0.68
    ades
    0.67
     bans
    0.67
    Act Density 0.150%

    No Known Activations