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

    Neuronpedia

    INDEX
    Explanations

    references to personal stories and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.02
    2:0.05
    3:0.29
    4:0.02
    5:0.12
    6:0.01
    7:0.05
    8:0.02
    9:0.02
    10:0.26
    11:0.02
    Negative Logits
     ineligible
    -2.29
     incumb
    -2.14
     PACs
    -2.07
    tarians
    -2.01
     Defendants
    -1.95
    acists
    -1.93
     Presumably
    -1.93
     Liberals
    -1.93
     exceptions
    -1.89
     incumbent
    -1.88
    POSITIVE LOGITS
     secrets
    2.84
     insights
    2.78
     discoveries
    2.56
     tips
    2.51
     wisdom
    2.49
     Secrets
    2.36
     findings
    2.36
     insight
    2.24
     discovery
    2.24
     thoughts
    2.23
    Act Density 0.079%

    No Known Activations