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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases that express a strong opinion or stance on a particular matter

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     targ
    -0.64
     Meridian
    -0.60
     Moons
    -0.60
     Malf
    -0.59
     Targ
    -0.59
     peaks
    -0.58
     hon
    -0.58
     Ocean
    -0.57
    umbs
    -0.56
    aged
    -0.56
    POSITIVE LOGITS
    ĸļ
    0.91
    senal
    0.89
    ::::::::
    0.88
    rael
    0.87
     hereby
    0.85
    etheless
    0.76
    Ļ½
    0.73
    actionDate
    0.72
    yip
    0.70
     nonetheless
    0.69
    Act Density 0.215%

    No Known Activations