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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific brand or product named "FX" with different variations in activations

    oai_token-act-pair · gpt-3.5-turbo

    references to the FX network or its programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adin
    -0.95
     carcin
    -0.73
     Fas
    -0.69
    izational
    -0.66
    alogue
    -0.66
    chen
    -0.65
     Astro
    -0.65
     Enrique
    -0.65
     McKenna
    -0.64
     Schne
    -0.63
    POSITIVE LOGITS
    FX
    0.93
    erity
    0.88
    ombies
    0.86
    ergus
    0.85
    fx
    0.80
    assi
    0.79
    uries
    0.76
    FP
    0.76
    SW
    0.75
    CG
    0.73
    Act Density 0.010%

    No Known Activations