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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal indicators or phrases that suggest a progression in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ​​
    -0.81
    venido
    -0.75
    occhio
    -0.74
     MonoBehaviour
    -0.73
    InputBorder
    -0.69
    nestjs
    -0.68
     Barbour
    -0.68
     nose
    -0.67
     McDonough
    -0.66
    stdc
    -0.63
    POSITIVE LOGITS
     later
    2.24
    later
    2.15
    Later
    2.12
     Later
    2.10
     LATER
    1.95
     senere
    1.50
     späteren
    1.45
     später
    1.44
    earlier
    1.42
     earlier
    1.42
    Act Density 0.067%

    No Known Activations