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

    Neuronpedia

    INDEX
    Explanations

    statements and opinions, often introduced with verbs like 'say', 'added', 'argued', 'claimed', 'went', 'said', 'contended', or 'noted'

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to statements and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prus
    -0.63
    adesh
    -0.58
    ptives
    -0.56
     confir
    -0.53
    speech
    -0.52
    ainted
    -0.49
    estern
    -0.49
    NL
    -0.49
    reporting
    -0.49
     teasp
    -0.48
    POSITIVE LOGITS
    ,
    0.89
    ,,
    0.82
    *,
    0.81
    ,[
    0.75
    .,
    0.73
    !,
    0.69
    ,—
    0.67
    ,...
    0.67
    ®,
    0.65
    ,-
    0.64
    Act Density 0.192%

    No Known Activations