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

    Neuronpedia

    INDEX
    Explanations

    words related to degrading or destructive actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "des" and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tipped
    -0.74
     Holmes
    -0.72
     Hastings
    -0.69
    OWS
    -0.66
    ancial
    -0.64
    STER
    -0.64
     caregivers
    -0.63
     Palmer
    -0.61
    glers
    -0.61
    DAY
    -0.60
    POSITIVE LOGITS
    ignt
    1.03
    plet
    1.02
    icc
    1.01
    ktop
    1.00
    ugar
    0.99
    ync
    0.98
    ription
    0.95
    ynchron
    0.93
    aturated
    0.92
    pell
    0.92
    Act Density 0.011%

    No Known Activations