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

    Neuronpedia

    INDEX
    Explanations

    references to information or data descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walkover
    -0.81
    isEqualTo
    -0.76
     Rasmussen
    -0.74
    gatsby
    -0.69
     Marra
    -0.69
    trische
    -0.68
     Daven
    -0.67
    guen
    -0.67
     Searle
    -0.67
     Ras
    -0.66
    POSITIVE LOGITS
     Info
    1.53
    Info
    1.47
    info
    1.47
     info
    1.40
    INFO
    1.36
     infos
    1.36
     getInfo
    1.31
     INFO
    1.26
    infos
    1.22
    ginfo
    1.16
    Act Density 0.034%

    No Known Activations