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

    Neuronpedia

    INDEX
    Explanations

    words related to announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "OU" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arians
    -0.89
    arian
    -0.67
    ucci
    -0.67
     Enemies
    -0.65
    aminer
    -0.63
    imus
    -0.63
     Angels
    -0.62
    onom
    -0.61
     Esper
    -0.61
     Pax
    -0.60
    POSITIVE LOGITS
    BLE
    1.05
    VEN
    1.01
    TH
    1.00
    THER
    0.97
    SE
    0.95
    LOS
    0.93
    LET
    0.93
    bled
    0.91
    TER
    0.90
    PDATE
    0.90
    Act Density 0.039%

    No Known Activations