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

    Neuronpedia

    INDEX
    Explanations

    sentences related to legal or criminal matters

    oai_token-act-pair · gpt-3.5-turbo

    conclusive statements and assessments within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.80
     overloaded
    -0.77
     biting
    -0.76
     rall
    -0.76
     pir
    -0.73
     unders
    -0.72
     submerged
    -0.72
     hunger
    -0.72
     seaf
    -0.70
     screwed
    -0.69
    POSITIVE LOGITS
     Logged
    1.27
    Reviewer
    1.23
     Flavoring
    1.18
     Specifically
    1.13
     Depending
    1.09
     Usually
    1.02
     Examples
    1.02
     Firstly
    1.00
    sbm
    1.00
     Typically
    1.00
    Act Density 0.116%

    No Known Activations