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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sal" with different suffixes and prefixes before or after the word "sal"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "salad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dominion
    -0.89
    lihood
    -0.84
    STEP
    -0.77
     Annotations
    -0.75
     Breed
    -0.75
    schild
    -0.71
    gaard
    -0.69
    STRUCT
    -0.69
     derog
    -0.68
    urden
    -0.67
    POSITIVE LOGITS
    mone
    1.06
    utations
    1.06
    isbury
    0.98
    istry
    0.95
    aunch
    0.95
    utation
    0.94
    udos
    0.94
    ience
    0.93
    adin
    0.92
    ient
    0.91
    Act Density 0.006%

    No Known Activations