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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "against."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERTY
    -0.68
    jména
    -0.65
     kasarigan
    -0.58
    談社
    -0.58
    SerializedSize
    -0.56
     Lucid
    -0.56
    nexo
    -0.56
    lala
    -0.55
    nemo
    -0.55
    umenical
    -0.55
    POSITIVE LOGITS
    Against
    1.74
     Against
    1.73
     against
    1.69
    against
    1.62
     AGAINST
    1.58
     contre
    1.22
     gegen
    1.21
     tegen
    1.02
     melawan
    0.99
     против
    0.91
    Act Density 0.166%

    No Known Activations