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

    Neuronpedia

    INDEX
    Explanations

    references to observational evidence in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISupport
    -0.55
    [++
    -0.48
    发表于
    -0.48
    Mixture
    -0.47
    GenerationType
    -0.47
    いった
    -0.46
     mixture
    -0.45
     ratio
    -0.44
    $_['
    -0.44
    навли
    -0.44
    POSITIVE LOGITS
    AnchorStyles
    0.69
    WebVitals
    0.68
     distant
    0.58
     situés
    0.56
     Distant
    0.56
    onAttach
    0.56
     تضيفلها
    0.56
    opsida
    0.55
     located
    0.54
     localised
    0.53
    Act Density 0.690%

    No Known Activations