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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hierarchical structures or organizational positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hierarchical structures or positions within groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argo
    -0.73
     toast
    -0.72
     Deal
    -0.67
     Breath
    -0.63
     Mub
    -0.62
    \/\/
    -0.62
     MAD
    -0.62
    ifa
    -0.60
    issance
    -0.59
     Pilgrim
    -0.59
    POSITIVE LOGITS
    hip
    0.85
    cius
    0.83
    ename
    0.83
    hips
    0.82
    paces
    0.80
    cape
    0.80
    pace
    0.79
     ranks
    0.78
    leading
    0.78
    naire
    0.77
    Act Density 0.024%

    No Known Activations