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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "later" to identify sequences of events or time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.20
    oter
    -0.16
    orns
    -0.16
    sWith
    -0.15
    licated
    -0.15
    yb
    -0.15
    rail
    -0.15
    yonel
    -0.15
    sis
    -0.15
    sel
    -0.15
    POSITIVE LOGITS
    -than
    0.25
    _than
    0.23
    most
    0.20
     than
    0.20
    than
    0.18
    anging
    0.18
    oom
    0.18
    -stage
    0.17
    wards
    0.17
    аÑĢÑħ
    0.16
    Act Density 0.020%

    No Known Activations