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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate past habits or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /use
    -0.17
    ÑĩиÑģл
    -0.16
    ando
    -0.15
    pell
    -0.15
    lse
    -0.15
    ROTO
    -0.15
    cke
    -0.15
    greg
    -0.14
    :UIAlert
    -0.14
    period
    -0.14
    POSITIVE LOGITS
     old
    0.26
    æŧ
    0.21
    .old
    0.21
    (old
    0.20
    -old
    0.20
    old
    0.20
    iani
    0.19
     used
    0.18
     to
    0.17
     formerly
    0.16
    Act Density 0.037%

    No Known Activations