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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "Cont" and variations thereof used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERAL
    -0.15
    chyb
    -0.14
    coat
    -0.14
    erap
    -0.14
    ERICA
    -0.14
    Å¡enÃŃ
    -0.14
    hack
    -0.14
    lename
    -0.13
    erk
    -0.13
    gnore
    -0.13
    POSITIVE LOGITS
    rovers
    0.43
    rolling
    0.40
    empl
    0.35
    emporary
    0.35
    empor
    0.34
    amination
    0.33
    amin
    0.32
    rollable
    0.32
    iguous
    0.31
    ested
    0.31
    Act Density 0.012%

    No Known Activations