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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "som"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "som" which indicates a focus on somatic experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Expansion
    -0.77
     Expand
    -0.73
    Ro
    -0.69
     Fill
    -0.65
    enos
    -0.64
    eno
    -0.64
     Garrett
    -0.64
     Barnett
    -0.64
     CRC
    -0.63
     Courier
    -0.63
    POSITIVE LOGITS
     som
    3.86
     Som
    1.22
     melanch
    1.04
     melancholy
    1.03
     SOM
    1.01
     skelet
    0.99
     leth
    0.96
     grim
    0.90
     contempl
    0.89
     bitters
    0.88
    Act Density 0.023%

    No Known Activations