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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing anticipation or excitement about future events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     objectionable
    -0.77
     negligible
    -0.71
     obscured
    -0.67
     flagged
    -0.65
     unconscious
    -0.65
    ELF
    -0.64
     median
    -0.64
    llan
    -0.63
    essential
    -0.63
     disappro
    -0.63
    POSITIVE LOGITS
    eday
    0.86
     rematch
    0.83
     explore
    0.82
     someday
    0.80
     adventure
    0.78
     hear
    0.78
    mble
    0.75
     learn
    0.75
     upcoming
    0.75
     possibilities
    0.73
    Act Density 0.115%

    No Known Activations