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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating influence or impact

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to providing assistance or carrying out tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    si
    -0.75
    ibrary
    -0.65
    icle
    -0.65
    OUP
    -0.64
    nings
    -0.64
    heimer
    -0.64
    ère
    -0.63
    shire
    -0.62
    eria
    -0.61
    efer
    -0.61
    POSITIVE LOGITS
     alike
    0.85
    redients
    0.76
     oneself
    0.72
     thereof
    0.71
    GGGGGGGG
    0.69
    quished
    0.68
     respectively
    0.66
     accordingly
    0.63
     orphans
    0.63
     conduc
    0.62
    Act Density 0.199%

    No Known Activations