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

    Neuronpedia

    INDEX
    Explanations

    phrases related to procedural or technical instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igshid
    -0.60
    <bos>
    -0.56
     Trains
    -0.44
     Train
    -0.44
     Wiktionnaire
    -0.44
    ⓧ
    -0.42
    train
    -0.41
    Train
    -0.41
    łk
    -0.40
    PerformLayout
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.73
     Roskov
    0.66
     متعلقه
    0.65
     exactamente
    0.65
    どういう
    0.62
    TagMode
    0.61
    Personendaten
    0.58
     فريبيس
    0.56
    ódz
    0.56
     exactly
    0.55
    Act Density 0.601%

    No Known Activations