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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating position or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _singleton
    -0.17
    angi
    -0.16
    _roi
    -0.14
    kom
    -0.14
    idel
    -0.14
    ertz
    -0.14
    idth
    -0.14
    anged
    -0.13
    nda
    -0.13
     acc
    -0.13
    POSITIVE LOGITS
     pitcher
    0.24
     Pitch
    0.21
     pitches
    0.20
    pitch
    0.20
     pitchers
    0.19
    Pitch
    0.19
     pitched
    0.18
     pitch
    0.18
    .pitch
    0.18
     pitching
    0.17
    Act Density 0.000%

    No Known Activations