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

    Neuronpedia

    INDEX
    Explanations

    terms related to caution or alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è°ĥ
    -0.17
    maal
    -0.15
    ä¿
    -0.15
     Bold
    -0.15
    formed
    -0.14
    Invariant
    -0.14
    ër
    -0.14
    má
    -0.14
    ÑģÑĭ
    -0.14
     Calder
    -0.13
    POSITIVE LOGITS
    ingly
    0.26
     signs
    0.23
     issued
    0.22
     bells
    0.21
    /alert
    0.20
     Signs
    0.19
     against
    0.19
     Iss
    0.19
     about
    0.19
    against
    0.18
    Act Density 0.033%

    No Known Activations