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

    Neuronpedia

    INDEX
    Explanations

    adverbs or adjectives related to deliberate or intentional actions

    oai_token-act-pair · gpt-3.5-turbo

    words indicating intentionality or deliberate action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soon
    -0.80
    addons
    -0.74
     Tycoon
    -0.71
    Score
    -0.70
    busters
    -0.69
     Citation
    -0.68
    esc
    -0.68
    til
    -0.67
    front
    -0.65
    rooms
    -0.65
    POSITIVE LOGITS
     misrepresent
    0.81
     misleading
    0.77
     reinvent
    0.77
    ãĤ©
    0.77
     fals
    0.76
     misled
    0.72
     coded
    0.72
     planted
    0.72
     omitted
    0.71
     obfusc
    0.71
    Act Density 0.019%

    No Known Activations