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

    Neuronpedia

    INDEX
    Explanations

    speech patterns with verbs and adverbs indicating manner

    oai_token-act-pair · gpt-3.5-turbo

    dialogue and direct speech elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.78
     underestimated
    -0.67
     maximal
    -0.66
     seminal
    -0.63
     discrep
    -0.63
     lucky
    -0.61
     violated
    -0.61
     discriminated
    -0.60
     neighb
    -0.60
     interfered
    -0.60
    POSITIVE LOGITS
     referring
    0.84
     paraph
    0.70
    åŃIJ
    0.69
     Aval
    0.68
     referencing
    0.66
     behalf
    0.66
    éģ
    0.66
     quoted
    0.65
    Said
    0.63
    phrase
    0.62
    Act Density 0.224%

    No Known Activations