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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "cr" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.87
     Polo
    -0.66
    EMENT
    -0.66
    Materials
    -0.64
     Helsinki
    -0.63
    olean
    -0.63
    DragonMagazine
    -0.63
     Rath
    -0.62
    ropolitan
    -0.61
     Werewolf
    -0.60
    POSITIVE LOGITS
    umb
    1.23
    umbs
    1.23
    umbled
    1.19
    umbles
    1.16
    ickets
    1.10
    anked
    1.10
    ump
    1.06
    umin
    1.03
    amping
    1.02
    utch
    1.00
    Act Density 0.013%

    No Known Activations