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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and low-level programming concepts related to software development

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.79
     InputDecoration
    -0.62
    alisco
    -0.61
    Aholisi
    -0.60
    GeneratedValue
    -0.58
     Administrativna
    -0.58
     tròn
    -0.58
     FontWeight
    -0.57
    VINCE
    -0.57
    plash
    -0.57
    POSITIVE LOGITS
    OGND
    0.73
     underlying
    0.73
     raw
    0.65
    underlying
    0.61
     Underlying
    0.55
     behind
    0.55
    Behind
    0.51
    behind
    0.50
     dietro
    0.50
    raw
    0.49
    Act Density 0.364%

    No Known Activations