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

    Neuronpedia

    INDEX
    Explanations

    expressions related to stability and continuity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoff
    -0.15
    OTTOM
    -0.15
    awy
    -0.14
    okie
    -0.14
    amak
    -0.13
    ẩm
    -0.13
    cken
    -0.13
    oval
    -0.13
    .glide
    -0.13
    주ìĿĺ
    -0.13
    POSITIVE LOGITS
     open
    1.02
     opened
    0.88
    -open
    0.87
    open
    0.87
     opens
    0.80
    .open
    0.79
     OPEN
    0.79
     opening
    0.78
    _open
    0.76
    opened
    0.73
    Act Density 0.284%

    No Known Activations