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

    Neuronpedia

    INDEX
    Explanations

    words related to physical condition and health

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical condition and health status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enge
    -0.77
    ruce
    -0.70
    hem
    -0.64
    umi
    -0.64
    rap
    -0.63
    û
    -0.62
    utters
    -0.61
    lem
    -0.60
    auc
    -0.60
     laun
    -0.59
    POSITIVE LOGITS
     financially
    0.73
    mia
    0.72
     Dragonbound
    0.67
    ness
    0.67
    ciating
    0.66
     Janeiro
    0.66
     mentally
    0.65
     handwriting
    0.64
     academ
    0.64
    FORMATION
    0.63
    Act Density 0.087%

    No Known Activations