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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Posted" that indicate updates or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ively
    -0.77
    ingly
    -0.75
    fitting
    -0.73
    ivo
    -0.72
    oller
    -0.71
    ãĥ¯ãĥ³
    -0.70
    ppard
    -0.70
    isky
    -0.68
    stood
    -0.68
    adier
    -0.68
    POSITIVE LOGITS
    itors
    0.73
    vertis
    0.71
    monton
    0.70
     Tue
    0.68
     Comments
    0.67
     Thu
    0.67
    Posted
    0.67
     Written
    0.67
    MON
    0.64
    Thu
    0.64
    Act Density 0.004%

    No Known Activations