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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ultimate
    -0.15
    chter
    -0.15
    onse
    -0.14
    kind
    -0.14
    urator
    -0.14
    оÑĢаз
    -0.14
    emas
    -0.13
    ober
    -0.13
    ult
    -0.13
    annot
    -0.13
    POSITIVE LOGITS
    lane
    0.16
     enough
    0.15
    -reaching
    0.15
     à¹Ĩ
    0.15
    ãģªãĤĭ
    0.15
    thest
    0.14
    .documentation
    0.14
    fold
    0.14
    rier
    0.14
    umi
    0.14
    Act Density 0.030%

    No Known Activations