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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing different groups of people or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.15
    ulin
    -0.14
    ATAB
    -0.14
     someone
    -0.14
    atte
    -0.14
    aign
    -0.14
    μον
    -0.14
    zdy
    -0.14
    ichni
    -0.14
    zig
    -0.14
    POSITIVE LOGITS
     whom
    0.33
     tomorrow
    0.24
     stature
    0.22
     yesterday
    0.20
     note
    0.18
     Tomorrow
    0.18
     color
    0.17
     today
    0.17
     who
    0.17
    /vendors
    0.17
    Act Density 0.100%

    No Known Activations