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

    Neuronpedia

    INDEX
    Explanations

    punctuation and transitions that indicate changes in thought or narrative direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilim
    -0.18
    dy
    -0.16
     now
    -0.15
     dy
    -0.15
     has
    -0.14
    VL
    -0.14
    usty
    -0.13
     will
    -0.13
    awy
    -0.13
    has
    -0.13
    POSITIVE LOGITS
    _Tis
    0.16
    _mD
    0.16
    ÅĽmy
    0.16
    amage
    0.15
    lý
    0.15
    ừa
    0.14
    _mE
    0.14
    .ToolTip
    0.14
    vatel
    0.14
     Upon
    0.14
    Act Density 0.178%

    No Known Activations