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

    Neuronpedia

    INDEX
    Explanations

    words related to intense actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social organization and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.74
    saw
    -0.67
    aughs
    -0.63
    assetsadobe
    -0.62
    arius
    -0.61
     greets
    -0.60
    awaru
    -0.60
    !/
    -0.57
    icipated
    -0.57
     Sins
    -0.57
    POSITIVE LOGITS
     obsolete
    0.99
     moot
    0.83
     unavailable
    0.82
    solete
    0.81
     faire
    0.80
     unus
    0.79
     accessible
    0.78
     inaccessible
    0.74
     safer
    0.74
     unatt
    0.74
    Act Density 0.454%

    No Known Activations