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

    Neuronpedia

    INDEX
    Explanations

    names containing the substring "air"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "air" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.68
     mov
    -0.61
     XII
    -0.59
    aptic
    -0.59
     electronically
    -0.58
    erg
    -0.57
    URES
    -0.57
     Hello
    -0.57
    ALK
    -0.57
     Unch
    -0.56
    POSITIVE LOGITS
    waves
    0.97
    cast
    0.96
    pin
    0.94
    bnb
    0.90
    neau
    0.89
    voy
    0.83
    clinton
    0.82
    fen
    0.81
    croft
    0.81
    bons
    0.81
    Act Density 0.048%

    No Known Activations