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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to possession or attribution

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Politics
    -0.69
     Angola
    -0.66
     Instruments
    -0.66
     Fine
    -0.61
     Panama
    -0.59
     Pearce
    -0.59
     Yellow
    -0.59
     Kell
    -0.58
     Ruin
    -0.58
     Chin
    -0.58
    POSITIVE LOGITS
    self
    1.36
    alian
    1.28
    selves
    1.12
    atic
    1.11
    atically
    1.10
    chy
    1.09
     selves
    0.97
    unes
    0.91
    asca
    0.90
    ELF
    0.88
    Act Density 0.217%

    No Known Activations