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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to being motionless or stationary

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "still."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alties
    -0.74
    insula
    -0.69
    ufact
    -0.69
    Course
    -0.67
     Distribution
    -0.66
    agus
    -0.66
    é¾
    -0.64
    ASE
    -0.63
    incial
    -0.63
     elimination
    -0.63
    POSITIVE LOGITS
    birth
    0.92
    born
    0.81
     alive
    0.80
    heres
    0.76
     intact
    0.76
     lifes
    0.74
     reeling
    0.67
    alia
    0.66
    adays
    0.66
     exists
    0.65
    Act Density 0.045%

    No Known Activations