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

    Neuronpedia

    INDEX
    Explanations

    verbs related to recounting events or statements

    oai_token-act-pair · gpt-3.5-turbo

    reported speech or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.70
    iral
    -0.70
    Ranked
    -0.70
    atform
    -0.69
    Pont
    -0.68
    pend
    -0.68
    Pub
    -0.68
    fruit
    -0.66
    SourceFile
    -0.65
    yet
    -0.65
    POSITIVE LOGITS
     she
    1.14
     he
    1.08
     afterward
    0.95
     they
    0.95
     goodbye
    0.92
     officers
    0.88
     hello
    0.87
     passers
    0.86
     afterwards
    0.83
     deputies
    0.81
    Act Density 0.151%

    No Known Activations