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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or judgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.69
     ILCS
    -0.67
     è£ıè¦ļéĨĴ
    -0.66
     paran
    -0.60
    Wilson
    -0.59
    estern
    -0.59
    å½
    -0.58
    ãĥ¯ãĥ³
    -0.57
    èĢħ
    -0.56
    è¦ļéĨĴ
    -0.56
    POSITIVE LOGITS
     ain
    1.32
     nonetheless
    1.23
     certainly
    1.22
     nevertheless
    1.22
     doesn
    1.21
     wasn
    1.19
     isn
    1.18
     does
    1.15
     shouldn
    1.14
     hasn
    1.14
    Act Density 0.111%

    No Known Activations