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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.44
     dads
    -0.42
    cdn
    -0.42
    birds
    -0.41
    tsky
    -0.40
    ball
    -0.39
    borg
    -0.38
    Cola
    -0.38
    vet
    -0.37
    bird
    -0.37
    POSITIVE LOGITS
    AMI
    0.57
    IENT
    0.51
    WER
    0.48
    hetical
    0.47
    ANC
    0.46
    OUN
    0.45
    ENS
    0.44
    OLOGY
    0.44
    chwitz
    0.43
    UTH
    0.43
    Act Density 0.115%

    No Known Activations