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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of leaving or the impact of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewire
    -0.18
    /from
    -0.16
    ierz
    -0.15
    oka
    -0.15
    ouser
    -0.15
    rap
    -0.15
    rien
    -0.14
    illery
    -0.14
    ácil
    -0.14
    à¸ł
    -0.14
    POSITIVE LOGITS
     behind
    0.43
     Behind
    0.34
    Behind
    0.31
    beh
    0.29
     aside
    0.28
     room
    0.25
    aside
    0.23
    _beh
    0.20
    -handed
    0.20
    room
    0.19
    Act Density 0.030%

    No Known Activations