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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identifying or describing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the state or condition of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondo
    -0.55
     disapp
    -0.54
     Enhancement
    -0.53
    ritz
    -0.52
    ampa
    -0.52
     applications
    -0.52
    ridges
    -0.50
     refreshed
    -0.50
     Comfort
    -0.49
     Butterfly
    -0.49
    POSITIVE LOGITS
     termed
    0.98
    uably
    0.81
     arguably
    0.79
     amounted
    0.79
    ivably
    0.77
    ensibly
    0.77
     admittedly
    0.74
     approx
    0.74
     billed
    0.73
     ordinarily
    0.73
    Act Density 0.206%

    No Known Activations