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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong opinion or action

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that end with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.69
     coerc
    -0.68
     overriding
    -0.66
     staggered
    -0.66
     numer
    -0.65
     convergence
    -0.65
     multiplier
    -0.65
    °
    -0.65
     inertia
    -0.64
     neighb
    -0.64
    POSITIVE LOGITS
     Said
    0.92
     âĢķ
    0.87
     Asked
    0.84
     Speak
    0.76
     Saying
    0.76
     Tears
    0.76
     Adds
    0.76
     Hearing
    0.75
     Exactly
    0.73
     Huh
    0.72
    Act Density 0.093%

    No Known Activations