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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating scheduled events or future plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    кÑĥп
    -0.15
    bose
    -0.15
    dea
    -0.14
    able
    -0.14
    aar
    -0.14
    ultan
    -0.14
    antee
    -0.14
    ลาà¸Ķ
    -0.14
    yle
    -0.14
    .INSTANCE
    -0.13
    POSITIVE LOGITS
     tent
    0.17
     Wald
    0.16
    cheduled
    0.15
    igon
    0.15
    -for
    0.15
     Lesser
    0.15
    edList
    0.15
    isay
    0.15
     Planned
    0.15
     Parenthood
    0.14
    Act Density 0.025%

    No Known Activations