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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "less" and its variations to identify themes of absence or deprivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Compute
    -0.16
    볬
    -0.15
    atz
    -0.15
    ongyang
    -0.15
    ansa
    -0.15
     negoci
    -0.14
    AndGet
    -0.14
    jac
    -0.14
    abe
    -0.14
    ладÑĥ
    -0.14
    POSITIVE LOGITS
    xing
    0.16
    vÄĽd
    0.15
    berman
    0.15
    nes
    0.15
     Lind
    0.15
    ime
    0.14
    ços
    0.14
    ife
    0.14
    esen
    0.14
    isol
    0.14
    Act Density 0.017%

    No Known Activations