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

    Neuronpedia

    INDEX
    Explanations

    verbs and expressions indicating actions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Breadcrumb
    -0.17
     Syn
    -0.15
    azor
    -0.15
    defgroup
    -0.15
    kud
    -0.14
     Enc
    -0.14
    immel
    -0.14
    å³
    -0.14
    ills
    -0.13
    .jpa
    -0.13
    POSITIVE LOGITS
     McCart
    0.19
    efon
    0.17
     behold
    0.17
    à¥įयत
    0.17
    feld
    0.16
     spare
    0.16
     worry
    0.15
    ÙĬÙĨÙĩ
    0.15
    entes
    0.15
    inkel
    0.14
    Act Density 0.083%

    No Known Activations