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

    Neuronpedia

    INDEX
    Explanations

    references to information-related keywords

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.79
    isEqualTo
    -0.68
    ovas
    -0.68
     Bowles
    -0.67
    guen
    -0.65
    ais
    -0.64
     Rasmussen
    -0.63
     Rees
    -0.62
    geren
    -0.61
    avut
    -0.61
    POSITIVE LOGITS
     تانيه
    0.98
    ginfo
    0.96
    PageInfo
    0.96
     Info
    0.91
    INFO
    0.85
     infos
    0.85
    ymce
    0.84
     zirconia
    0.82
    info
    0.79
     info
    0.79
    Act Density 0.016%

    No Known Activations