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

    Neuronpedia

    INDEX
    Explanations

    programming syntax or code structure

    oai_token-act-pair · gpt-3.5-turbo

    specific repetitive symbols or characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĭ
    -0.70
    DAQ
    -0.66
    çīĪ
    -0.64
    GY
    -0.64
    hattan
    -0.62
     Naz
    -0.61
     Seeking
    -0.60
     Pavilion
    -0.59
     guiActiveUnfocused
    -0.59
     Tid
    -0.59
    POSITIVE LOGITS
    almost
    0.84
    certain
    0.78
    been
    0.78
    perhaps
    0.76
    £
    0.74
    his
    0.74
    should
    0.72
    ķ
    0.71
    ¡
    0.70
    say
    0.70
    Act Density 0.332%

    No Known Activations