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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-improvement and personal effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -scrollbar
    -0.16
    à¸Ļม
    -0.16
    venir
    -0.15
    erece
    -0.14
    ãģŁãĤī
    -0.14
    Compression
    -0.14
    586
    -0.14
     cord
    -0.14
    .backward
    -0.14
    ẹn
    -0.14
    POSITIVE LOGITS
     yourself
    0.17
     Yourself
    0.16
    oco
    0.15
    urette
    0.15
    ocale
    0.15
    ama
    0.15
    MD
    0.15
    Łèĥ½
    0.14
    ings
    0.14
    rng
    0.14
    Act Density 0.184%

    No Known Activations