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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mechanical or electrical components and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inflate
    -0.16
    .synthetic
    -0.15
    akat
    -0.14
    ãĥ£
    -0.14
     Yuan
    -0.14
    spar
    -0.14
     inflation
    -0.14
     Suarez
    -0.14
    ock
    -0.13
     haz
    -0.13
    POSITIVE LOGITS
     wind
    0.51
    wind
    0.46
    Wind
    0.44
     winding
    0.43
     wound
    0.42
     Wind
    0.41
    _wind
    0.37
     winds
    0.36
    .wind
    0.34
     windy
    0.32
    Act Density 0.032%

    No Known Activations