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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific verbs and their forms, particularly associated with ownership and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.80
    EStreamFrame
    -0.74
    lished
    -0.73
    ĺħ
    -0.67
    âĶĢâĶĢ
    -0.67
    ç·
    -0.66
     discharge
    -0.65
     trave
    -0.64
    Gaza
    -0.63
    Closure
    -0.63
    POSITIVE LOGITS
    lem
    0.89
    ilon
    0.89
    rag
    0.85
    acher
    0.85
    away
    0.82
    lems
    0.80
    eren
    0.79
    eh
    0.77
    iston
    0.77
    agen
    0.76
    Act Density 0.142%

    No Known Activations