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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vs
    -0.16
     Hass
    -0.16
    hma
    -0.15
    ariat
    -0.15
    vas
    -0.15
     loot
    -0.14
    adb
    -0.14
    ercul
    -0.14
    acon
    -0.14
    vos
    -0.14
    POSITIVE LOGITS
     dokonce
    0.16
     Gür
    0.15
    ahlen
    0.15
    .ToolTip
    0.15
     incluso
    0.14
    aukee
    0.14
    haps
    0.14
     even
    0.14
     nawet
    0.14
     Pods
    0.14
    Act Density 0.079%

    No Known Activations