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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of silencing or being silenced

    oai_token-act-pair · gpt-3.5-turbo

    references to silence and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oti
    -0.80
     Klu
    -0.69
    kin
    -0.66
     Investment
    -0.63
    lik
    -0.62
    pects
    -0.61
     skilled
    -0.59
     Roller
    -0.59
     Bun
    -0.58
     Enh
    -0.58
    POSITIVE LOGITS
     silence
    4.40
     Silence
    2.58
     silent
    1.96
     silenced
    1.60
     quiet
    1.58
     solitude
    1.51
     secrecy
    1.51
     inaction
    1.48
     mute
    1.43
     indifference
    1.29
    Act Density 0.026%

    No Known Activations