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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "point" and its variations indicating direction or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hover
    -0.16
    hol
    -0.15
    Ïİν
    -0.15
    hed
    -0.15
    orp
    -0.15
     ug
    -0.14
    isson
    -0.14
    ences
    -0.14
    ifle
    -0.14
    iciel
    -0.14
    POSITIVE LOGITS
    lashes
    0.17
    živ
    0.16
    ersh
    0.14
    ycastle
    0.14
    :Set
    0.14
    iddy
    0.14
    ERS
    0.14
    خص
    0.14
    eba
    0.13
    داÙħ
    0.13
    Act Density 0.015%

    No Known Activations