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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to specific locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mechanically
    -0.73
     normalized
    -0.68
    PLAY
    -0.67
     AMERICA
    -0.67
     flaw
    -0.66
     fictitious
    -0.65
     predictable
    -0.64
     scratch
    -0.64
     brake
    -0.64
     frantic
    -0.64
    POSITIVE LOGITS
    hai
    1.36
    ai
    1.36
    oa
    1.33
    onga
    1.29
    oi
    1.26
    aru
    1.25
    ku
    1.24
    ui
    1.21
    apa
    1.21
    wana
    1.21
    Act Density 0.344%

    No Known Activations