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

    Neuronpedia

    INDEX
    Explanations

    URLs or web addresses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs and domain names in web addresses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.94
    posedge
    -0.93
    IntoConstraints
    -0.93
     Italijani
    -0.81
     <<<<<<<<<<<<<<
    -0.80
     betweenstory
    -0.80
    AISSEE
    -0.79
    Hochspringen
    -0.78
    TypedDataSet
    -0.78
    ="@+
    -0.77
    POSITIVE LOGITS
    .
    0.39
    root
    0.39
     heavily
    0.32
    isHidden
    0.31
    ühren
    0.30
     embarazada
    0.29
     Elemente
    0.29
     cruzado
    0.29
    正确的
    0.28
     Universitaria
    0.28
    Act Density 0.064%

    No Known Activations