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

    Neuronpedia

    INDEX
    Explanations

    words related to physical impacts or collisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bump" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mechdragon
    -0.72
    RIP
    -0.70
    ufact
    -0.70
    uve
    -0.65
     Lauder
    -0.65
    éĸ
    -0.65
    ILLE
    -0.65
     [|
    -0.63
    encia
    -0.63
    ndra
    -0.63
    POSITIVE LOGITS
    kins
    1.38
    kin
    1.37
    ster
    0.94
    stakes
    0.91
    hift
    0.88
    balls
    0.88
    sters
    0.87
    stick
    0.82
    rint
    0.82
    started
    0.81
    Act Density 0.089%

    No Known Activations