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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs and phrases that suggest actions or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spar
    -0.17
    lear
    -0.17
    aza
    -0.16
    iliz
    -0.16
    _SIGNATURE
    -0.15
    ãĥ¼ãĤ¹
    -0.15
    mart
    -0.15
    WithPath
    -0.15
    isyon
    -0.15
     ;č↵
    -0.14
    POSITIVE LOGITS
    ouro
    0.19
     oneself
    0.16
    onen
    0.14
     Ñģебе
    0.14
    ohen
    0.14
     Ones
    0.13
     entitlement
    0.13
    ivist
    0.13
    upiter
    0.13
    enna
    0.13
    Act Density 0.165%

    No Known Activations