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

    Neuronpedia

    INDEX
    Explanations

    terms related to tokenization in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Esk
    -0.16
    uum
    -0.15
    JECT
    -0.15
    inan
    -0.15
    rost
    -0.14
     khẩu
    -0.14
    raig
    -0.14
    Strict
    -0.14
    aret
    -0.14
    riel
    -0.14
    POSITIVE LOGITS
    оÑĢоз
    0.20
    rance
    0.15
    OTH
    0.15
    TypeName
    0.14
    eless
    0.14
    onto
    0.14
    oth
    0.14
    gend
    0.14
    cker
    0.14
    isia
    0.14
    Act Density 0.009%

    No Known Activations