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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns followed by a verb, possibly related to decision-making or consequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Torn
    -0.74
     Orn
    -0.72
     Rusty
    -0.68
     Fine
    -0.67
     Corpus
    -0.64
     Absent
    -0.63
    package
    -0.63
     Bian
    -0.62
     Invisible
    -0.62
     Unic
    -0.61
    POSITIVE LOGITS
    alian
    0.99
     relates
    0.95
     happened
    0.84
     beh
    0.83
    unes
    0.79
     transpired
    0.79
     happens
    0.79
    ÃĥÃĤ
    0.79
    umbnails
    0.78
     pains
    0.76
    Act Density 0.091%

    No Known Activations