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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables within equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ارش
    -0.15
     znam
    -0.15
    ÅĻet
    -0.15
    hod
    -0.15
    nar
    -0.14
    -positive
    -0.14
    [++
    -0.14
    positive
    -0.14
    ikel
    -0.13
    Ãły
    -0.13
    POSITIVE LOGITS
     -
    0.44
     minus
    0.41
     –
    0.32
     âĪĴ
    0.27
    minus
    0.27
    .subtract
    0.26
     -↵
    0.24
    _-_
    0.23
    Minus
    0.23
    _minus
    0.23
    Act Density 0.149%

    No Known Activations