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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or states of being in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewan
    -0.17
     earlier
    -0.15
     Earlier
    -0.15
    recent
    -0.15
    tras
    -0.15
    æĹ©
    -0.14
     kenn
    -0.14
     once
    -0.14
     recently
    -0.14
    esk
    -0.14
    POSITIVE LOGITS
     until
    0.48
    until
    0.40
     Until
    0.40
    Until
    0.38
     till
    0.35
     jusqu
    0.34
    _until
    0.33
     até
    0.33
     hasta
    0.32
    .until
    0.27
    Act Density 0.143%

    No Known Activations