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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and derivatives in related scientific content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krom
    -0.17
    achuset
    -0.15
    ieur
    -0.15
    itesse
    -0.14
    åIJĪ
    -0.14
    uell
    -0.14
    inski
    -0.14
    ýt
    -0.14
    ynos
    -0.13
    uke
    -0.13
    POSITIVE LOGITS
    257
    0.16
    odied
    0.15
    Ĥ¤
    0.15
    à¹Ģย
    0.15
    287
    0.15
    ovky
    0.14
    odge
    0.14
    173
    0.14
    202
    0.14
     Run
    0.14
    Act Density 0.036%

    No Known Activations