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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "later" and its variants in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.21
     latest
    -0.20
     recent
    -0.19
     earlier
    -0.19
     lately
    -0.19
     early
    -0.18
    sis
    -0.18
    sb
    -0.16
     ever
    -0.16
    ritch
    -0.16
    POSITIVE LOGITS
    ally
    0.37
    ality
    0.27
    -stage
    0.27
    ALLY
    0.24
    -than
    0.24
    -day
    0.21
     stages
    0.21
    -on
    0.20
    _than
    0.19
    -life
    0.18
    Act Density 0.039%

    No Known Activations