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

    Neuronpedia

    INDEX
    Explanations

    phrases describing personal experiences and recounts of events

    oai_token-act-pair · gpt-3.5-turbo

    narratives about personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antam
    -0.76
    aligned
    -0.72
    phasis
    -0.69
    ocracy
    -0.68
    iciency
    -0.68
     Radius
    -0.68
    FML
    -0.65
    tarian
    -0.65
    tarians
    -0.64
    ardless
    -0.64
    POSITIVE LOGITS
     anecdotes
    1.94
     stories
    1.85
     tales
    1.84
     anecdote
    1.56
    stories
    1.56
     memories
    1.51
     tale
    1.37
     story
    1.36
     secrets
    1.34
     testimonies
    1.34
    Act Density 0.385%

    No Known Activations