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

    Neuronpedia

    INDEX
    Explanations

    proper names with surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or notable personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.75
    ossier
    -0.72
    ournal
    -0.68
    ablishment
    -0.67
    ggle
    -0.66
    angered
    -0.66
    acebook
    -0.65
     corrid
    -0.65
    Mrs
    -0.63
    undai
    -0.63
    POSITIVE LOGITS
     III
    1.05
     Jr
    0.99
    gren
    0.88
     (@
    0.88
    burn
    0.85
     aka
    0.84
     QC
    0.83
     II
    0.80
     Morse
    0.80
    berg
    0.79
    Act Density 0.224%

    No Known Activations