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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving or walking away from a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to walking away or leaving a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gae
    -0.70
     backdrop
    -0.70
    illary
    -0.69
    doi
    -0.67
    ellation
    -0.66
    umn
    -0.65
    oly
    -0.65
    ionic
    -0.64
    umbers
    -0.62
    GY
    -0.61
    POSITIVE LOGITS
     from
    0.79
     safely
    0.77
     peacefully
    0.77
     unnoticed
    0.76
     victorious
    0.76
    RAG
    0.69
     unsc
    0.68
     Jagu
    0.67
     unin
    0.66
     unsatisf
    0.66
    Act Density 0.034%

    No Known Activations