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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (&:
    -0.61
    DebuggerStep
    -0.55
    andExpect
    -0.54
     themſelves
    -0.54
    ſelves
    -0.54
     ElementRef
    -0.53
     earliest
    -0.53
     houſe
    -0.52
    HtmlAttribute
    -0.52
     whoſe
    -0.52
    POSITIVE LOGITS
     whatsoever
    0.69
    burger
    0.66
     more
    0.64
     special
    0.62
     ventured
    0.61
     fancy
    0.61
     short
    0.61
     less
    0.60
     beats
    0.59
    Демографія
    0.59
    Act Density 0.095%

    No Known Activations