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

    Neuronpedia

    INDEX
    Explanations

    elements of performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¹Ħ
    -0.15
    acho
    -0.15
    ongoose
    -0.14
    ält
    -0.14
    APON
    -0.14
    ughty
    -0.13
    seite
    -0.13
    ensibly
    -0.13
    agne
    -0.13
    ancock
    -0.13
    POSITIVE LOGITS
    SR
    0.27
    HR
    0.25
    xr
    0.24
    är
    0.24
    гаÑĢ
    0.24
    IR
    0.24
    lr
    0.23
    sr
    0.23
    yar
    0.23
     JR
    0.23
    Act Density 0.229%

    No Known Activations