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

    Neuronpedia

    INDEX
    Explanations

    phrases and references related to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atsby
    -0.18
    hend
    -0.16
    ross
    -0.15
    ucid
    -0.15
    reon
    -0.15
    baugh
    -0.14
    Ñħи
    -0.14
     Attend
    -0.14
     spy
    -0.14
    ROSS
    -0.14
    POSITIVE LOGITS
     depths
    0.15
    .docker
    0.15
    ipt
    0.14
    Dark
    0.13
    ecer
    0.13
    ูม
    0.13
     Hashtable
    0.13
    帮
    0.13
     Nah
    0.13
    etable
    0.13
    Act Density 0.199%

    No Known Activations