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

    Neuronpedia

    INDEX
    Explanations

    elements related to queries, expectations, and desires expressed in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajs
    -0.15
    isation
    -0.14
    icity
    -0.14
    ryo
    -0.14
     же
    -0.14
    веÑī
    -0.14
    евеÑĢ
    -0.14
    گاÙĨÛĮ
    -0.14
    ality
    -0.14
    ’s
    -0.14
    POSITIVE LOGITS
     them
    0.31
     him
    0.29
    (ed
    0.27
    /do
    0.26
    /use
    0.24
    /create
    0.23
    /find
    0.23
     regarding
    0.23
    /read
    0.22
    /manage
    0.22
    Act Density 0.377%

    No Known Activations