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

    Neuronpedia

    INDEX
    Explanations

    words related to making a decision or taking action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "go for" followed by various contexts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    below
    -0.68
    LCS
    -0.67
    âĶĢâĶĢâĶĢâĶĢ
    -0.67
    Introduced
    -0.67
    âĶĢ
    -0.66
    ould
    -0.66
    ogether
    -0.65
    §
    -0.64
    ,.
    -0.64
    ###
    -0.63
    POSITIVE LOGITS
    bidden
    1.05
     hire
    0.97
    geries
    0.88
    WARD
    0.87
     example
    0.84
    gotten
    0.79
     starters
    0.77
     inspiration
    0.73
    gery
    0.73
     awhile
    0.73
    Act Density 0.104%

    No Known Activations