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

    Neuronpedia

    INDEX
    Explanations

    terms related to activism or reasons for a particular situation

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "cause" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seasons
    -0.72
    Ku
    -0.70
    PDATE
    -0.68
    illet
    -0.68
    atari
    -0.65
    Ħ¢
    -0.64
     Storm
    -0.64
     Sachs
    -0.63
    CHAT
    -0.63
     Schwar
    -0.63
    POSITIVE LOGITS
     cele
    1.46
    way
    0.83
    ality
    0.80
    cause
    0.80
     celeb
    0.78
    umed
    0.73
    llor
    0.72
    forge
    0.71
    vier
    0.70
    unity
    0.70
    Act Density 0.036%

    No Known Activations