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

    Neuronpedia

    INDEX
    Explanations

    terms related to generalizations and broad concepts in academic or theoretical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AME
    -0.14
    reo
    -0.13
    ame
    -0.13
    othy
    -0.13
    LM
    -0.13
     essentially
    -0.13
    assage
    -0.13
    atel
    -0.13
    CTOR
    -0.13
     pat
    -0.13
    POSITIVE LOGITS
    -purpose
    0.19
    angl
    0.16
    /general
    0.15
    å®Ī
    0.15
    adder
    0.15
    _defined
    0.15
    ocus
    0.14
    zed
    0.14
    Delegate
    0.14
    iz
    0.14
    Act Density 0.047%

    No Known Activations