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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal transitions or moments of realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦÙĤ
    -0.15
    gne
    -0.15
    ognito
    -0.14
    nyder
    -0.14
    ancell
    -0.14
    amiliar
    -0.13
    åĶ
    -0.13
    nor
    -0.13
    ugin
    -0.13
    .fragments
    -0.13
    POSITIVE LOGITS
    here
    0.32
    adays
    0.26
    HERE
    0.23
    days
    0.20
    withstanding
    0.19
     comes
    0.19
    onder
    0.18
    onto
    0.18
     onto
    0.18
     imagine
    0.18
    Act Density 0.031%

    No Known Activations