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

    Neuronpedia

    INDEX
    Explanations

    phrases related to avoiding actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of avoidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.80
    rooms
    -0.78
    soon
    -0.73
    iop
    -0.71
    cart
    -0.70
    Haunted
    -0.70
    essee
    -0.69
    lease
    -0.69
    si
    -0.68
    church
    -0.68
    POSITIVE LOGITS
     pitfalls
    1.08
     detection
    1.04
     wasting
    0.88
     relegation
    0.81
     collisions
    0.80
     answering
    0.80
    ably
    0.78
     hazards
    0.77
     fou
    0.76
     contamin
    0.75
    Act Density 0.050%

    No Known Activations