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

    Neuronpedia

    INDEX
    Explanations

    phrases related to new appointments or leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    new successor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.56
    astify
    -0.52
    ArgsConstructor
    -0.49
    onomía
    -0.48
    PathVariable
    -0.46
    Ārējās
    -0.45
    nasel
    -0.45
     iNdEx
    -0.45
    sizeCache
    -0.45
     باخ
    -0.45
    POSITIVE LOGITS
     newOwner
    0.53
    #
    0.44
     reemplazo
    0.41
     CANDIDATE
    0.40
     candidate
    0.39
    transQ
    0.38
    cyclopedia
    0.38
     remplacement
    0.38
     *++
    0.37
    ]")]
    0.35
    Act Density 0.041%

    No Known Activations