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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TextBoxColumn
    -0.79
    SerializedSize
    -0.77
     Wil
    -0.75
    sterious
    -0.75
    clerview
    -0.73
     Dons
    -0.72
    homonymie
    -0.72
    )_/¯
    -0.72
     NgModule
    -0.71
    [];
    -0.71
    POSITIVE LOGITS
     HERE
    1.53
     Here
    1.47
     here
    1.44
    HERE
    1.42
    Here
    1.41
    here
    1.41
     aqui
    1.22
     Aquí
    1.20
     aquí
    1.16
    Aqui
    1.13
    Act Density 0.066%

    No Known Activations