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

    Neuronpedia

    INDEX
    Explanations

    statements of opinions or reactions, often characterized by specific phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '-';↵
    -0.14
     '/';↵
    -0.14
    },{↵
    -0.13
     "/"↵
    -0.13
    VOID
    -0.12
    ozor
    -0.12
    ado
    -0.12
    à¸Īาà¸ģà¸ģาร
    -0.12
     ith
    -0.12
    éĽħé»ij
    -0.12
    POSITIVE LOGITS
     "
    0.46
     “
    0.38
     '
    0.34
    ãĢĮ
    0.27
     ``
    0.26
     ‘
    0.26
     `
    0.25
     \"
    0.25
     «
    0.24
    ãĢĮæĪij
    0.24
    Act Density 0.535%

    No Known Activations