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

    Neuronpedia

    INDEX
    Explanations

    verbs related to revealing or exposing something

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of disclosing or uncovering information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wake
    -0.71
    otor
    -0.70
    annis
    -0.68
    atomic
    -0.68
    acqu
    -0.67
    hovah
    -0.65
    yip
    -0.64
    agues
    -0.64
    upiter
    -0.62
    ucky
    -0.62
    POSITIVE LOGITS
     loopholes
    0.90
     secrets
    0.86
    orial
    0.86
     truths
    0.83
    ibility
    0.83
     flaws
    0.82
     weaknesses
    0.79
    ively
    0.77
    iveness
    0.77
     revelations
    0.73
    Act Density 0.057%

    No Known Activations