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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating excessiveness or overwhelming feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mp
    -0.15
    lot
    -0.15
    licht
    -0.15
    ussen
    -0.14
    ry
    -0.14
    ávÄĽ
    -0.14
    ford
    -0.14
    phan
    -0.14
    patch
    -0.14
    ullo
    -0.14
    POSITIVE LOGITS
     much
    0.31
    led
    0.27
     Much
    0.26
    Much
    0.24
    much
    0.24
     soon
    0.23
     MUCH
    0.21
     many
    0.21
    oooo
    0.21
     late
    0.20
    Act Density 0.036%

    No Known Activations