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

    Neuronpedia

    INDEX
    Explanations

    instances of the characters Ċ and Ļ

    oai_token-act-pair · gpt-3.5-turbo

    subjective assessments and expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brid
    -0.86
     eleph
    -0.86
     displacement
    -0.86
     dubbed
    -0.82
    ¥ŀ
    -0.82
     specialized
    -0.80
     advancing
    -0.79
     migration
    -0.77
     periodic
    -0.77
     designated
    -0.77
    POSITIVE LOGITS
    Anyway
    2.05
    Advertisements
    1.74
    Seriously
    1.67
    Yeah
    1.66
    Maybe
    1.59
    Honestly
    1.59
    HAHA
    1.58
    Okay
    1.57
    Fuck
    1.56
    Advertisement
    1.52
    Act Density 0.326%

    No Known Activations