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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a transition in time or a continuation of a narrative

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.81
    amsung
    -0.72
    etsk
    -0.69
     awaits
    -0.68
    wait
    -0.67
     reside
    -0.67
     greeted
    -0.66
     solves
    -0.64
     âĢº
    -0.63
     waited
    -0.63
    POSITIVE LOGITS
     same
    0.95
     sheer
    0.91
     slightest
    0.87
     widest
    0.86
     latter
    0.85
     usual
    0.85
     outset
    0.81
     onset
    0.79
     end
    0.78
     aforementioned
    0.78
    Act Density 0.102%

    No Known Activations