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

    Neuronpedia

    INDEX
    Explanations

    terms related to generalizations and theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imm
    -0.16
    kel
    -0.14
     Quar
    -0.14
     Imm
    -0.14
    phia
    -0.14
    ibs
    -0.14
     Wich
    -0.13
    ular
    -0.13
     formation
    -0.13
    ante
    -0.13
    POSITIVE LOGITS
    .MSG
    0.15
    reetings
    0.15
    Ñĥди
    0.14
    zim
    0.14
    ties
    0.14
     Maintain
    0.14
     braces
    0.13
    ghi
    0.13
    APON
    0.13
    onec
    0.13
    Act Density 0.026%

    No Known Activations