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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing events or situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating awareness and understanding of significant events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -0.73
    aments
    -0.72
    lication
    -0.70
    Los
    -0.70
    few
    -0.70
    hedon
    -0.69
    ttes
    -0.69
    inker
    -0.66
    ikers
    -0.66
    gart
    -0.65
    POSITIVE LOGITS
    piring
    0.80
     happening
    0.78
    pires
    0.77
     entails
    0.71
     transpired
    0.70
     dstg
    0.67
     litter
    0.65
     Happ
    0.64
     cov
    0.63
     happen
    0.62
    Act Density 0.210%

    No Known Activations