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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "man" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tone
    -0.21
    yaw
    -0.18
    ATIC
    -0.17
    y
    -0.16
    ted
    -0.16
    tach
    -0.16
    yen
    -0.15
    sense
    -0.15
    tt
    -0.15
    ounder
    -0.15
    POSITIVE LOGITS
    agements
    0.34
    tras
    0.33
    agment
    0.31
    made
    0.31
    hattan
    0.31
    ufac
    0.30
    handling
    0.29
    chester
    0.29
    handled
    0.28
    hole
    0.28
    Act Density 0.018%

    No Known Activations