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

    Neuronpedia

    INDEX
    Explanations

    words related to questioning or expressing doubt

    oai_token-act-pair · gpt-3.5-turbo

    the word "really" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atre
    -0.76
    enary
    -0.72
    ifully
    -0.71
    illary
    -0.67
    osi
    -0.62
    iously
    -0.62
    ican
    -0.61
    ately
    -0.61
    Transaction
    -0.61
    et
    -0.60
    POSITIVE LOGITS
    polit
    0.77
    ignment
    0.75
     behaved
    0.75
     cared
    0.75
     ought
    0.74
     existed
    0.73
    hya
    0.72
     meant
    0.70
     mattered
    0.70
    FTWARE
    0.69
    Act Density 0.053%

    No Known Activations