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

    Neuronpedia

    INDEX
    Explanations

    expressions of faith and confidence in oneself and others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĥĵ
    -0.16
    ÌĤ
    -0.16
    ewise
    -0.15
    GMEM
    -0.15
    anson
    -0.15
    elson
    -0.14
    agner
    -0.14
     Helm
    -0.14
    ward
    -0.14
    ziel
    -0.14
    POSITIVE LOGITS
    pus
    0.18
    Ix
    0.15
     Lucia
    0.15
     Chi
    0.15
     chi
    0.14
    148
    0.14
    perf
    0.14
    AndGet
    0.14
    worth
    0.14
    agus
    0.14
    Act Density 0.051%

    No Known Activations