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

    Neuronpedia

    INDEX
    Explanations

    phrases related to departure or moving on from past situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BorderColor
    -0.17
    vertime
    -0.15
    azzi
    -0.15
    afka
    -0.15
     ì°¸
    -0.14
    itals
    -0.14
    scribe
    -0.14
     [[]
    -0.14
    à¸ļ
    -0.14
    Serializable
    -0.14
    POSITIVE LOGITS
     behind
    1.12
     Behind
    0.95
    Behind
    0.84
    beh
    0.71
     achter
    0.56
     rear
    0.52
     hinter
    0.42
     posterior
    0.41
     پشت
    0.41
     backend
    0.39
    Act Density 0.079%

    No Known Activations