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

    Neuronpedia

    INDEX
    Explanations

    references to information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     couver
    -0.75
     Daven
    -0.74
    ized
    -0.73
     Burrows
    -0.71
    Madeleine
    -0.71
     Searle
    -0.71
     Rasmussen
    -0.70
     Glaser
    -0.70
    RepeatedField
    -0.69
    ele
    -0.69
    POSITIVE LOGITS
     infos
    0.99
     Info
    0.98
     getInfo
    0.91
    ginfo
    0.91
    infos
    0.90
    INFO
    0.88
    info
    0.88
     Infos
    0.88
     INFO
    0.86
     info
    0.85
    Act Density 0.035%

    No Known Activations