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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or gradual change in position

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of drifting or wandering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourt
    -0.72
    urat
    -0.71
    erion
    -0.70
    reon
    -0.66
    ilings
    -0.65
    avez
    -0.64
    amines
    -0.64
    rices
    -0.64
    byn
    -0.63
    orate
    -0.63
    POSITIVE LOGITS
    lust
    1.14
    wood
    0.95
     drifting
    0.84
     drift
    0.79
     Rover
    0.77
    luster
    0.76
     wandering
    0.74
    GGGG
    0.73
    abouts
    0.73
     away
    0.72
    Act Density 0.026%

    No Known Activations