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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate responses to medical treatments or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    typed
    -0.07
    IGENCE
    -0.07
    _typ
    -0.07
    opus
    -0.07
    urge
    -0.07
    amarin
    -0.07
    unda
    -0.07
    pone
    -0.07
    ủng
    -0.07
    evi
    -0.07
    POSITIVE LOGITS
    brief
    0.06
     اÙĨت
    0.06
    KK
    0.06
    ASE
    0.05
    \Bundle
    0.05
     cheers
    0.05
    Pes
    0.05
    UserDefaults
    0.05
     gag
    0.05
     humid
    0.05
    Act Density 0.007%

    No Known Activations