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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words associated with walking or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inous
    -0.78
    vous
    -0.76
    accompanied
    -0.75
    irl
    -0.72
    naissance
    -0.70
    ule
    -0.67
    ²¾
    -0.66
    upt
    -0.64
    rise
    -0.63
    employed
    -0.62
    POSITIVE LOGITS
     bounds
    0.85
     halls
    0.84
     aisle
    0.75
    ards
    0.73
     threshold
    0.73
    auntlet
    0.68
     thresholds
    0.67
    agons
    0.67
    stones
    0.67
     ethical
    0.66
    Act Density 0.116%

    No Known Activations