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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal awareness or realization

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their use in conveying personal beliefs or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aston
    -0.78
    haps
    -0.70
    noon
    -0.67
    phans
    -0.65
    elia
    -0.62
    bender
    -0.62
    Mont
    -0.62
    quartered
    -0.60
    hattan
    -0.59
    WHO
    -0.58
    POSITIVE LOGITS
     wrought
    0.86
     happ
    0.84
     happened
    0.81
     happen
    0.81
     learnt
    0.79
     happens
    0.75
    've
    0.74
     wanted
    0.74
     learned
    0.74
    'd
    0.72
    Act Density 0.133%

    No Known Activations