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

    Neuronpedia

    INDEX
    Explanations

    verbs related to positive or beneficial actions and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to improving or mitigating negative conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mad
    -0.68
    tw
    -0.65
     prow
    -0.64
     mull
    -0.63
    Ëľ
    -0.61
     possessed
    -0.60
     consulted
    -0.60
     headlined
    -0.59
     struck
    -0.57
    Û
    -0.57
    POSITIVE LOGITS
    hift
    0.85
    uces
    0.79
    rontal
    0.77
    ategory
    0.77
     tremend
    0.74
     unwanted
    0.73
     circulation
    0.72
    glers
    0.72
    vantage
    0.72
    ierrez
    0.72
    Act Density 0.321%

    No Known Activations