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

    Neuronpedia

    INDEX
    Explanations

    relationships and interactions between people and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HideFlags
    -0.59
    rawDesc
    -0.53
    ьаж
    -0.53
     '\\;'
    -0.50
    <bos>
    -0.49
     arrep
    -0.48
     Relaxed
    -0.47
    RTEE
    -0.47
     raso
    -0.47
    IUrlHelper
    -0.47
    POSITIVE LOGITS
     others
    0.75
     someone
    0.69
    someone
    0.68
    Someone
    0.67
     Someone
    0.65
     other
    0.59
    Somebody
    0.59
    somebody
    0.58
    others
    0.56
     somebody
    0.55
    Act Density 0.133%

    No Known Activations