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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing denial or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.51
    LookAnd
    -0.51
    :✨
    -0.48
    webElementXpaths
    -0.47
    GEBURTSDATUM
    -0.46
     nakalista
    -0.45
    FirstResponder
    -0.44
     الرياضيه
    -0.44
     tremendously
    -0.40
     kasarigan
    -0.40
    POSITIVE LOGITS
    
    0.44
     لينك
    0.44
     anymore
    0.42
    care
    0.38
     reconciled
    0.38
     slightest
    0.38
     superfluous
    0.38
    Cyfeiriadau
    0.38
     care
    0.37
     Notice
    0.36
    Act Density 0.067%

    No Known Activations