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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns or words related to ownership

    oai_token-act-pair · gpt-3.5-turbo

    words related to positioning and framing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    die
    -0.71
    ylum
    -0.65
    iya
    -0.65
    cus
    -0.64
    yrus
    -0.62
    edom
    -0.61
    iyah
    -0.60
    aghd
    -0.59
    \'
    -0.58
    aceae
    -0.57
    POSITIVE LOGITS
    matically
    0.83
    Ī
    0.83
    urally
    0.81
     accordingly
    0.78
    uate
    0.76
     differently
    0.75
    eering
    0.74
     appropriately
    0.74
    senal
    0.73
     oneself
    0.72
    Act Density 0.216%

    No Known Activations