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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" indicating intention or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Howe
    -0.18
    prod
    -0.15
    ci
    -0.15
    oo
    -0.14
    ehler
    -0.14
    519
    -0.14
    oe
    -0.14
    hash
    -0.13
    id
    -0.13
    ud
    -0.13
    POSITIVE LOGITS
    asers
    0.19
    ãĥ¡ãĥ³ãĥĪ
    0.17
    .scalablytyped
    0.16
    mant
    0.15
    ertools
    0.15
    iley
    0.14
    è¦
    0.14
    enever
    0.14
    entes
    0.14
    _thr
    0.14
    Act Density 0.000%

    No Known Activations