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

    Neuronpedia

    INDEX
    Explanations

    events or situations where something changes direction or improves

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "turn around" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.85
     tatt
    -0.71
    PLIED
    -0.65
    iston
    -0.65
    rought
    -0.63
    accompan
    -0.62
     Born
    -0.62
    hip
    -0.61
     tattoo
    -0.60
    gel
    -0.60
    POSITIVE LOGITS
    wagen
    0.87
    atform
    0.79
    gressive
    0.77
    ernaut
    0.75
    µ
    0.73
    ivas
    0.72
    allery
    0.72
    ichick
    0.68
    itect
    0.64
    oots
    0.64
    Act Density 0.015%

    No Known Activations