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

    Neuronpedia

    INDEX
    Explanations

    actionable instructions and parameters related to tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Immediate
    -0.16
    wig
    -0.16
     immediate
    -0.16
     eventual
    -0.16
     soon
    -0.15
    \Bridge
    -0.15
     eventually
    -0.15
    ooter
    -0.15
    veau
    -0.14
    ointments
    -0.14
    POSITIVE LOGITS
    (before
    0.17
    åħĪ
    0.17
    -before
    0.17
    /pre
    0.16
     pré
    0.15
    AVA
    0.15
    LOCKS
    0.15
    verty
    0.15
    before
    0.15
    pre
    0.14
    Act Density 0.076%

    No Known Activations