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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions, such as recusal and exoneration

    oai_token-act-pair · gpt-3.5-turbo

    words related to refusal or rejecting involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raltar
    -0.73
    amac
    -0.70
    inyl
    -0.68
    aic
    -0.68
    melon
    -0.65
    ppa
    -0.63
    oppy
    -0.63
    ancial
    -0.63
    yssey
    -0.62
    ersed
    -0.61
    POSITIVE LOGITS
     perjury
    0.82
    enary
    0.80
    owship
    0.76
    hee
    0.74
     grace
    0.69
     narrator
    0.68
     exoner
    0.68
    urate
    0.67
    uries
    0.67
    iate
    0.67
    Act Density 0.074%

    No Known Activations