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

    Neuronpedia

    INDEX
    Explanations

    phrases related to detachment, escaping, and walking away from situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbers
    -0.76
    ounce
    -0.67
    enegger
    -0.61
    ãĥ¥
    -0.58
    immer
    -0.57
    iop
    -0.57
    cycl
    -0.56
    tone
    -0.56
    amar
    -0.56
    wave
    -0.55
    POSITIVE LOGITS
     from
    1.13
     FROM
    1.06
    from
    1.01
    From
    0.96
     From
    0.94
    away
    0.82
    ired
    0.78
    owship
    0.75
    heid
    0.72
    iable
    0.72
    Act Density 2.093%

    No Known Activations