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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting the beginning or introduction of a discussion or action

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "let's" used to suggest starting or taking action on a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     holiest
    -0.78
     Soldier
    -0.67
    oppable
    -0.67
    PLIED
    -0.65
    AGES
    -0.63
    atana
    -0.63
     millenn
    -0.60
    CLASSIFIED
    -0.60
     cumbers
    -0.59
    manship
    -0.59
    POSITIVE LOGITS
    tered
    0.91
    icia
    0.90
    tering
    0.83
    itia
    0.82
    itans
    0.76
    ting
    0.76
     us
    0.75
    arius
    0.70
    oss
    0.70
    ersen
    0.69
    Act Density 0.026%

    No Known Activations