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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or exploration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating objectives or methods for acquiring knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥIJ
    -0.66
     squares
    -0.64
     towels
    -0.62
     feces
    -0.60
     benches
    -0.58
     drowned
    -0.58
     veins
    -0.58
     Croat
    -0.57
    ãģ®ç
    -0.56
     peas
    -0.56
    POSITIVE LOGITS
    INESS
    0.69
    iona
    0.68
    ocious
    0.66
    uce
    0.65
     Higher
    0.65
    umar
    0.65
    ocard
    0.63
    ocation
    0.63
    FK
    0.63
     Ratio
    0.62
    Act Density 0.336%

    No Known Activations