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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a high level of acclaim or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     really
    -0.15
    oy
    -0.14
    åij³
    -0.14
     Opt
    -0.14
    front
    -0.14
     hearty
    -0.14
    ikit
    -0.14
     rang
    -0.14
     lod
    -0.14
     crowds
    -0.14
    POSITIVE LOGITS
    irth
    0.17
     regarded
    0.17
     combust
    0.16
    liga
    0.15
    Carthy
    0.15
    apı
    0.15
    _patches
    0.15
    caffe
    0.15
    acket
    0.14
    -reg
    0.14
    Act Density 0.014%

    No Known Activations