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

    Neuronpedia

    INDEX
    Explanations

    information related to specific dates or events

    oai_token-act-pair · gpt-3.5-turbo

    events involving accidents or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.80
     Bake
    -0.65
     Emin
    -0.64
     Maxim
    -0.63
    Dim
    -0.63
    tiny
    -0.60
     maxim
    -0.60
     Babel
    -0.60
     Disciple
    -0.60
    orem
    -0.60
    POSITIVE LOGITS
    okemon
    0.77
    anwhile
    0.64
    uters
    0.62
    hester
    0.60
    anamo
    0.60
    AMI
    0.59
    joining
    0.58
    staking
    0.58
    .............
    0.57
    nered
    0.57
    Act Density 0.165%

    No Known Activations