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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and value placed on journalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sapp
    -0.69
     sovere
    -0.65
     envis
    -0.64
     âĢİ
    -0.63
    rem
    -0.63
    ment
    -0.63
     recourse
    -0.61
     mentally
    -0.61
     nonetheless
    -0.59
     whichever
    -0.59
    POSITIVE LOGITS
    ĸļ
    0.93
    ļéĨĴ
    0.84
    interstitial
    0.77
    utra
    0.76
    Static
    0.72
    margin
    0.69
    oric
    0.69
    arter
    0.68
    ioxide
    0.68
    Balt
    0.67
    Act Density 0.035%

    No Known Activations