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

    Neuronpedia

    INDEX
    Explanations

    words related to efficiency and detail-oriented attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ει
    -0.16
    SSI
    -0.15
    iteur
    -0.15
    ODO
    -0.15
    uler
    -0.14
     tako
    -0.14
    ragon
    -0.14
    odore
    -0.14
    isi
    -0.14
    resse
    -0.14
    POSITIVE LOGITS
    -to
    0.76
    -To
    0.56
    _to
    0.49
     To
    0.46
    To
    0.44
    .to
    0.40
    to
    0.39
    _To
    0.37
    _TO
    0.35
     to
    0.31
    Act Density 0.236%

    No Known Activations