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

    Neuronpedia

    INDEX
    Explanations

    words related to borders and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibur
    -0.74
    ocker
    -0.74
    inen
    -0.67
    alle
    -0.65
    士
    -0.64
    ested
    -0.63
    etic
    -0.63
    frey
    -0.62
    ests
    -0.62
    andum
    -0.61
    POSITIVE LOGITS
    stones
    0.95
    lines
    0.91
    oslov
    0.78
    Rect
    0.78
    line
    0.76
    oreal
    0.76
    acters
    0.74
    stone
    0.69
     Beir
    0.67
    lands
    0.67
    Act Density 0.012%

    No Known Activations