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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "after" and its variations, indicating a focus on events or actions following others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _codegen
    -0.16
    .joda
    -0.16
    .Magenta
    -0.15
    ashing
    -0.14
    killer
    -0.14
    Occurs
    -0.14
    inesis
    -0.14
    essler
    -0.14
    amen
    -0.13
    clerosis
    -0.13
    POSITIVE LOGITS
     having
    0.24
     previous
    0.23
     recent
    0.22
     being
    0.20
     earlier
    0.19
    Having
    0.18
    having
    0.18
     Previous
    0.17
     Having
    0.16
     last
    0.16
    Act Density 0.087%

    No Known Activations