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

    Neuronpedia

    INDEX
    Explanations

    features related to user preferences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.18
    IMS
    -0.16
     Profession
    -0.16
    URE
    -0.15
    ovnÄĽ
    -0.15
    ugi
    -0.14
    edla
    -0.14
    ynes
    -0.14
    geois
    -0.14
    oref
    -0.14
    POSITIVE LOGITS
     Cor
    0.17
    –
    0.16
     Alley
    0.15
    aton
    0.15
     redirects
    0.15
     è±
    0.15
    ĥĿ
    0.15
     elektron
    0.14
    ode
    0.14
    heck
    0.14
    Act Density 0.000%

    No Known Activations