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

    Neuronpedia

    INDEX
    Explanations

    instances of the special character "Å" followed by another character

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or concepts related to philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.76
    wards
    -0.74
     Commodore
    -0.69
    wagen
    -0.67
    iflower
    -0.66
     guiActiveUnfocused
    -0.65
    nels
    -0.63
     Coliseum
    -0.62
    espie
    -0.62
     certs
    -0.61
    POSITIVE LOGITS
    ½
    1.34
    Ĵ
    1.33
    ¼
    1.31
    ģ
    1.30
    »
    1.23
    ł
    1.22
    Į
    1.21
    ¾
    1.21
    ĵ
    1.20
    ļ
    1.20
    Act Density 0.005%

    No Known Activations