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

    Neuronpedia

    INDEX
    Explanations

    instances of the abbreviation "Es" or its variations, reflecting a preference for specific prefixes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhn
    -0.16
    ÑĤом
    -0.15
    croft
    -0.15
    Checkpoint
    -0.15
    avigation
    -0.14
    cry
    -0.14
    ataire
    -0.14
    uzzle
    -0.14
    yntax
    -0.14
     Struct
    -0.14
    POSITIVE LOGITS
    oteric
    0.26
    pecially
    0.25
    ablish
    0.21
    ophage
    0.20
    prit
    0.18
    SENT
    0.18
    sex
    0.17
    _ES
    0.17
    ENTIAL
    0.17
    cher
    0.17
    Act Density 0.017%

    No Known Activations