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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'W' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouncer
    -0.17
    actionDate
    -0.17
    chyb
    -0.15
    _vlog
    -0.15
    duino
    -0.15
    ecture
    -0.14
    apter
    -0.14
    #ac
    -0.14
    rå
    -0.14
     Plains
    -0.14
    POSITIVE LOGITS
    eren
    0.30
    ere
    0.26
    ant
    0.26
    ishing
    0.25
    ould
    0.25
    orry
    0.25
    anna
    0.24
    asting
    0.24
    ants
    0.24
    ished
    0.24
    Act Density 0.028%

    No Known Activations