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

    Neuronpedia

    INDEX
    Explanations

    phrases related to architecture and structures

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Arch" and its various forms in relation to architecture or entities associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.74
    berman
    -0.72
    ggle
    -0.71
    ffee
    -0.70
    cci
    -0.70
    chy
    -0.68
    Reloaded
    -0.67
    CRIPTION
    -0.67
     sterling
    -0.66
    âķIJâķIJ
    -0.65
    POSITIVE LOGITS
    itect
    1.18
     Arch
    1.12
    ipel
    1.07
    atech
    0.95
    alis
    0.79
    lake
    0.78
    Arch
    0.78
    arch
    0.77
    isd
    0.77
     arch
    0.76
    Act Density 0.007%

    No Known Activations