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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making a point, expressing beliefs, and emphasizing ideas

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that denote relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bones
    -0.66
     gorilla
    -0.65
     Aliens
    -0.63
    elsen
    -0.60
    minster
    -0.59
     Rouge
    -0.59
     Growth
    -0.58
     consolidation
    -0.58
    sterdam
    -0.57
     Cavs
    -0.57
    POSITIVE LOGITS
    Ïī
    0.77
     sidx
    0.71
    isable
    0.70
    Initialized
    0.70
    itten
    0.70
    ÃŁ
    0.68
    osher
    0.66
    athed
    0.66
    abal
    0.65
    sic
    0.65
    Act Density 0.758%

    No Known Activations