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

    Neuronpedia

    INDEX
    Explanations

    keywords related to implicit meanings or suggestions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    frey
    -0.86
    ppa
    -0.79
    meric
    -0.78
    mir
    -0.75
    gard
    -0.74
    ishers
    -0.72
    riot
    -0.71
    Ĥ¬
    -0.69
     Flavoring
    -0.68
    adan
    -0.68
    POSITIVE LOGITS
     consent
    0.86
     guiActiveUn
    0.86
     endorsement
    0.82
     acknowledgment
    0.81
     coupling
    0.79
     acknowledgement
    0.79
     assumption
    0.78
     implicitly
    0.77
     imply
    0.76
     implied
    0.75
    Act Density 0.071%

    No Known Activations