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

    Neuronpedia

    INDEX
    Explanations

    phrases related to descriptions and historical events, particularly regarding significant figures and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okie
    -0.16
    avl
    -0.16
     Kiev
    -0.16
     Laud
    -0.15
    aval
    -0.15
    uv
    -0.15
    gy
    -0.15
    aurant
    -0.14
    enant
    -0.14
    alte
    -0.14
    POSITIVE LOGITS
     Ali
    1.13
    Ali
    1.00
     ali
    0.86
    ali
    0.76
     Alien
    0.68
    ALI
    0.66
     aliens
    0.65
    .ali
    0.64
     alien
    0.62
     عÙĦÙĬ
    0.54
    Act Density 0.135%

    No Known Activations