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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decay or decline

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deterioration and decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.76
    usha
    -0.74
    ãĥĦ
    -0.71
    bara
    -0.71
    ounters
    -0.70
    poon
    -0.70
    pload
    -0.69
    pole
    -0.69
    ullivan
    -0.69
    abel
    -0.68
    POSITIVE LOGITS
     degradation
    0.98
     deteriorated
    0.98
     deterioration
    0.92
    gradation
    0.89
     deteriorating
    0.82
     decay
    0.82
     psychiat
    0.81
     degraded
    0.80
     untreated
    0.75
     decaying
    0.75
    Act Density 0.050%

    No Known Activations