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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific intentions or goals that are directed towards a target or outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote intentions or objectives related to various initiatives or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.75
    note
    -0.69
    orce
    -0.66
    assed
    -0.66
    umbered
    -0.65
    ensed
    -0.65
    notations
    -0.64
    lys
    -0.64
     whence
    -0.62
    Guard
    -0.61
    POSITIVE LOGITS
     maximizing
    0.74
     Sacrifice
    0.70
     narrowing
    0.69
    ggle
    0.69
    venge
    0.68
     specificity
    0.68
     simplicity
    0.67
     rewarding
    0.66
     gratification
    0.64
    Aim
    0.64
    Act Density 0.184%

    No Known Activations