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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement and consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ytic
    -0.17
    adge
    -0.16
    oret
    -0.15
    MLE
    -0.15
    .mybatisplus
    -0.15
    bé
    -0.14
    dro
    -0.14
    Regs
    -0.14
    /dr
    -0.14
    volt
    -0.14
    POSITIVE LOGITS
    ance
    0.21
    ably
    0.18
    EMENT
    0.18
    ement
    0.17
    aves
    0.16
    icut
    0.16
     to
    0.16
    /dis
    0.16
    anced
    0.16
    SSION
    0.15
    Act Density 0.030%

    No Known Activations