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

    Neuronpedia

    INDEX
    Explanations

    programming languages or frameworks

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that connect ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughter
    -0.76
     ingred
    -0.75
     indu
    -0.75
    umbnails
    -0.73
    utive
    -0.71
    cffffcc
    -0.70
     arri
    -0.69
     therap
    -0.69
    lict
    -0.68
    ãĤĵ
    -0.68
    POSITIVE LOGITS
     Shell
    0.93
     Torch
    0.92
     Glacier
    0.92
     Bleach
    0.92
     Banana
    0.92
     Firefly
    0.90
     Camel
    0.90
     Flavoring
    0.89
     Duck
    0.89
     Chrom
    0.88
    Act Density 0.325%

    No Known Activations