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

    Neuronpedia

    INDEX
    Explanations

    action verbs expressing accomplishment or achievement

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes related to taking initiative or addressing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.74
    see
    -0.67
    ,—
    -0.63
    Dim
    -0.61
    Ultra
    -0.58
    RET
    -0.58
    dim
    -0.58
    uti
    -0.57
    ère
    -0.56
    redo
    -0.55
    POSITIVE LOGITS
     oneself
    0.72
    ealous
    0.70
    inventoryQuantity
    0.65
    anchester
    0.62
    ococ
    0.61
    ©¶æ
    0.61
     Nem
    0.60
    ctions
    0.60
    helps
    0.59
    aquin
    0.59
    Act Density 0.175%

    No Known Activations