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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in the format of parenthesis with a number inside

    oai_token-act-pair · gpt-3.5-turbo

    list items or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advertis
    -0.68
     grocer
    -0.65
    agall
    -0.65
     rigging
    -0.62
    nam
    -0.62
    rentices
    -0.61
    buck
    -0.60
     grooming
    -0.59
     bos
    -0.59
    jug
    -0.59
    POSITIVE LOGITS
     [+
    0.99
    NK
    0.68
    eous
    0.67
    Pg
    0.64
    º
    0.64
    ãĤ´ãĥ³
    0.63
    ????
    0.63
     Whilst
    0.63
     Prot
    0.62
    %:
    0.62
    Act Density 0.023%

    No Known Activations