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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the action of putting something in a specific place or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "put in" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ľ
    -0.78
    ŀ
    -0.70
    STER
    -0.63
    Ł
    -0.63
    catentry
    -0.62
    enance
    -0.62
     TDs
    -0.60
    ¿½
    -0.60
    llor
    -0.60
    caster
    -0.60
    POSITIVE LOGITS
     jeopardy
    1.04
     lieu
    0.95
    ordinate
    0.92
    sole
    0.90
    humane
    0.89
     front
    0.85
    operative
    0.85
     accordance
    0.84
    escap
    0.82
    organic
    0.82
    Act Density 0.085%

    No Known Activations