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

    Neuronpedia

    INDEX
    Explanations

    statistical comparisons and measurements in scientific data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andre
    -0.16
    ofile
    -0.15
    reeze
    -0.15
    á»įc
    -0.15
    ogene
    -0.14
    chy
    -0.14
    redient
    -0.14
    arrass
    -0.14
    UX
    -0.14
    ocy
    -0.14
    POSITIVE LOGITS
    ãĥ«ãĥķ
    0.15
    thinkable
    0.15
    Tank
    0.15
    ëį
    0.14
     Tank
    0.14
    izu
    0.14
    zza
    0.13
    ãĥ³ãĤ¯
    0.13
    itsu
    0.13
    sten
    0.13
    Act Density 0.088%

    No Known Activations