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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rale
    -0.15
     prototypes
    -0.15
    eria
    -0.14
    enson
    -0.14
    oline
    -0.14
    rib
    -0.14
    MDB
    -0.14
    abant
    -0.14
    osate
    -0.14
    trib
    -0.13
    POSITIVE LOGITS
    åij½
    0.16
    .LENGTH
    0.16
    ooks
    0.15
    ó
    0.15
    xin
    0.15
    adera
    0.14
    iens
    0.14
    æī±
    0.14
    _PRINTF
    0.14
    gles
    0.14
    Act Density 0.091%

    No Known Activations