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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or plans being put into effect

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with legislative or procedural processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.66
    iverse
    -0.65
    rame
    -0.63
    iera
    -0.62
    asm
    -0.61
    gerald
    -0.60
    geries
    -0.59
    ervative
    -0.59
    ordinate
    -0.57
    vre
    -0.57
    POSITIVE LOGITS
     thereof
    1.20
     of
    1.16
    of
    0.90
     timelines
    0.89
     purposes
    0.87
     rates
    0.86
     procedures
    0.82
     mechanisms
    0.82
    Of
    0.82
    ism
    0.80
    Act Density 0.270%

    No Known Activations