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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or difficulty in recollection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igest
    -0.18
    nore
    -0.16
    vi
    -0.14
    _iff
    -0.14
    ertz
    -0.13
    itä
    -0.13
    idual
    -0.13
    view
    -0.13
     views
    -0.13
    astes
    -0.12
    POSITIVE LOGITS
     off
    0.26
     immediately
    0.23
    examples
    0.21
     examples
    0.20
     immediate
    0.20
     instantly
    0.20
     readily
    0.19
    atham
    0.19
    Examples
    0.19
     exact
    0.18
    Act Density 0.167%

    No Known Activations