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

    Neuronpedia

    INDEX
    Explanations

    the word "victory" with different contexts and intensities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "victory"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pores
    -0.74
    venants
    -0.67
    ussen
    -0.66
    asus
    -0.66
    umn
    -0.66
     notor
    -0.65
    effic
    -0.65
    hemy
    -0.64
    redits
    -0.63
    ridges
    -0.63
    POSITIVE LOGITS
     victory
    0.82
    Sham
    0.79
    hower
    0.78
    stroke
    0.77
     defeat
    0.76
     victories
    0.72
     Frieza
    0.71
    antly
    0.70
    bringer
    0.70
    isconsin
    0.70
    Act Density 0.016%

    No Known Activations