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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email newsletters

    oai_token-act-pair · gpt-3.5-turbo

    references to newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -0.64
     reformed
    -0.60
     Gaw
    -0.59
     Ow
    -0.58
     Catalyst
    -0.57
     barg
    -0.55
     fortun
    -0.53
     Galile
    -0.53
     ord
    -0.52
     Camel
    -0.52
    POSITIVE LOGITS
    usalem
    0.74
    veyard
    0.73
     actionGroup
    0.71
    isode
    0.70
     IMAGES
    0.69
    sylv
    0.68
    é¾įå¥ij士
    0.66
    umbnails
    0.66
    ļéĨĴ
    0.64
    ĸļ
    0.63
    Act Density 0.015%

    No Known Activations