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

    Neuronpedia

    INDEX
    Explanations

    implicit or tacit references

    oai_token-act-pair · gpt-3.5-turbo

    references to implicit biases and underlying assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frey
    -0.89
    meric
    -0.88
    mir
    -0.78
    tis
    -0.75
    cture
    -0.74
    ppa
    -0.73
     Flavoring
    -0.73
    gard
    -0.72
    cellence
    -0.69
     CrossRef
    -0.68
    POSITIVE LOGITS
     consent
    1.03
     acknowledgement
    1.01
     endorsement
    1.00
     acknowledgment
    0.97
     assumption
    0.95
     implicit
    0.89
     assumptions
    0.86
    icit
    0.86
     disav
    0.85
     encouragement
    0.85
    Act Density 0.048%

    No Known Activations