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

    Neuronpedia

    INDEX
    Explanations

    information related to experimental setup and methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ::_('
    -0.87
    ModelAdmin
    -0.74
    发表于
    -0.71
     يتيمه
    -0.70
    adaptiveStyles
    -0.69
    NameInMap
    -0.64
     Administrativna
    -0.64
    WriteLiteral
    -0.63
    OneToMany
    -0.63
    AxisAlignment
    -0.60
    POSITIVE LOGITS
     péri
    0.46
    iedenis
    0.46
     an
    0.46
    atív
    0.44
     tắt
    0.43
     einfach
    0.43
    forgotten
    0.43
     simpel
    0.43
     localizada
    0.42
    dagogik
    0.42
    Act Density 0.619%

    No Known Activations