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

    Neuronpedia

    INDEX
    Explanations

    verbs and adjectives related to direct actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    language that emphasizes direct actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ety
    -0.85
     Syndrome
    -0.77
    ney
    -0.74
    wich
    -0.72
    anooga
    -0.69
     outwe
    -0.67
     Frie
    -0.65
     scales
    -0.65
    aly
    -0.64
     Scores
    -0.63
    POSITIVE LOGITS
     direct
    3.57
     indirect
    2.18
    direct
    2.15
     Direct
    2.13
    Direct
    1.74
     DIRECT
    1.60
     directly
    1.52
     directed
    1.38
     directing
    1.29
     immediate
    1.23
    Act Density 0.022%

    No Known Activations