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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "told."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.78
    engeance
    -0.71
    pite
    -0.70
    otion
    -0.69
    icons
    -0.66
    abilities
    -0.66
    adesh
    -0.65
    cdn
    -0.63
    marine
    -0.63
    tan
    -0.63
    POSITIVE LOGITS
    tale
    1.10
    tell
    0.93
    told
    0.92
     told
    0.86
    warn
    0.86
     tells
    0.83
    soType
    0.81
     Tell
    0.77
    vale
    0.76
     bluntly
    0.76
    Act Density 0.058%

    No Known Activations