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

    Neuronpedia

    INDEX
    Explanations

    words related to suggesting or proposing an action or idea

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "suggested" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.69
    aliation
    -0.69
    fare
    -0.68
    vin
    -0.68
    respective
    -0.67
    mb
    -0.66
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.65
    Mania
    -0.63
    WHERE
    -0.63
     Ern
    -0.63
    POSITIVE LOGITS
    ible
    0.83
    ively
    0.81
    ibility
    0.77
     suggestions
    0.72
    ATIVE
    0.70
    antle
    0.68
     hints
    0.67
    kinson
    0.67
    ations
    0.67
    uggest
    0.67
    Act Density 0.038%

    No Known Activations