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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hence
    -0.15
    ायन
    -0.14
    iales
    -0.14
    ระ
    -0.14
    ôm
    -0.14
     WithEvents
    -0.13
    ναÏĤ
    -0.13
    øj
    -0.13
    ocy
    -0.13
    olf
    -0.13
    POSITIVE LOGITS
     want
    0.34
     Want
    0.33
     Need
    0.33
    Want
    0.33
     need
    0.31
    Need
    0.30
     Got
    0.29
    want
    0.29
     ready
    0.27
    Got
    0.26
    Act Density 0.095%

    No Known Activations