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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contradiction or opposition in arguments or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perature
    -0.64
    atimes
    -0.57
    HEAST
    -0.57
    NewUrlParser
    -0.55
    קישורים
    -0.54
     rộng
    -0.52
    tagHelperRunner
    -0.51
    ledem
    -0.49
    Carriera
    -0.49
     footprint
    -0.48
    POSITIVE LOGITS
     against
    1.33
     contrary
    1.27
     opposes
    1.26
     Against
    1.26
    Against
    1.24
    against
    1.21
     oppose
    1.21
     AGAINST
    1.16
     contre
    1.14
     opposed
    1.13
    Act Density 0.299%

    No Known Activations