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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acceptance or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "grade" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.80
     Lei
    -0.72
    eer
    -0.68
     quo
    -0.65
    ĸļ
    -0.62
    ership
    -0.60
     shortened
    -0.57
     Metall
    -0.56
     surveillance
    -0.56
     Bie
    -0.56
    POSITIVE LOGITS
    iffin
    1.35
    anted
    1.25
    ayson
    1.19
    udge
    1.19
    anny
    1.19
    umpy
    1.14
    iff
    1.13
    ace
    1.13
    ateful
    1.13
    untled
    1.13
    Act Density 0.023%

    No Known Activations