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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of revealing or disclosing information

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "reveal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otor
    -0.71
    atomic
    -0.71
    wake
    -0.71
     captcha
    -0.70
    yip
    -0.69
    enza
    -0.67
    acqu
    -0.66
    annis
    -0.66
     paced
    -0.66
    jet
    -0.65
    POSITIVE LOGITS
     loopholes
    0.91
     secrets
    0.81
     truths
    0.79
    ively
    0.78
    ibility
    0.77
     contradictions
    0.76
    iveness
    0.74
     weaknesses
    0.73
    orial
    0.73
     microphones
    0.72
    Act Density 0.035%

    No Known Activations