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

    Neuronpedia

    INDEX
    Explanations

    terminology related to prediction and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apa
    -0.17
    ãģĵãģĿ
    -0.16
    ty
    -0.15
    eras
    -0.15
    kan
    -0.15
    reator
    -0.15
    ola
    -0.14
    aku
    -0.14
    alog
    -0.14
    uation
    -0.14
    POSITIVE LOGITS
    /back
    0.17
    etter
    0.17
    posit
    0.17
    est
    0.17
    ed
    0.17
    igne
    0.15
    444
    0.15
    биÑĤ
    0.14
    iginal
    0.14
    edly
    0.14
    Act Density 0.033%

    No Known Activations