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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unn
    -0.15
    .opensource
    -0.14
    Ðĩ
    -0.14
    _mtx
    -0.14
    jectives
    -0.14
     Armor
    -0.14
    vé
    -0.14
    .Unicode
    -0.14
    zel
    -0.14
    unate
    -0.14
    POSITIVE LOGITS
     this
    0.20
     thus
    0.19
     This
    0.18
    This
    0.18
    è¿Ļç§į
    0.17
    Sounds
    0.16
    outil
    0.15
    -this
    0.15
    this
    0.15
    _this
    0.15
    Act Density 0.448%

    No Known Activations