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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate capability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahren
    -0.15
    ometr
    -0.15
    cia
    -0.15
    .Flag
    -0.14
    ách
    -0.14
    usement
    -0.14
    avana
    -0.14
    ë§ŀ
    -0.14
    åıªè¦ģ
    -0.14
    ulings
    -0.14
    POSITIVE LOGITS
    lant
    0.18
    berger
    0.17
    伯
    0.16
    769
    0.14
     outright
    0.14
    iza
    0.14
     anytime
    0.13
     Surely
    0.13
    ld
    0.13
    ORS
    0.13
    Act Density 0.151%

    No Known Activations