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

    Neuronpedia

    INDEX
    Explanations

    expressions of willingness or encouragement to try something new

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëģ
    -0.17
    tro
    -0.16
    sov
    -0.16
    eyim
    -0.14
    ìĸ
    -0.13
    .mvp
    -0.13
    akin
    -0.13
    ecurity
    -0.13
    AspNet
    -0.13
    MPI
    -0.13
    POSITIVE LOGITS
     shot
    0.27
     whirl
    0.25
     spin
    0.24
    shot
    0.24
     try
    0.23
    try
    0.22
     ago
    0.21
    Shot
    0.20
     Shot
    0.20
     Try
    0.18
    Act Density 0.020%

    No Known Activations