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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olland
    -0.16
    aternity
    -0.15
    bjerg
    -0.15
     Fact
    -0.15
    ences
    -0.15
    ificates
    -0.15
    uner
    -0.15
    ested
    -0.15
    estroy
    -0.15
    Ðİ
    -0.15
    POSITIVE LOGITS
    er
    0.24
    ative
    0.23
    radio
    0.20
    back
    0.20
     radio
    0.20
    ATIVE
    0.19
    ies
    0.18
     Radio
    0.18
    bubble
    0.18
    SPORT
    0.18
    Act Density 0.014%

    No Known Activations