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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AGMA
    -0.16
    enos
    -0.16
     higher
    -0.15
    баÑĩ
    -0.15
    egin
    -0.15
    aghan
    -0.15
    gz
    -0.15
    åįĵ
    -0.15
     approx
    -0.15
    nock
    -0.15
    POSITIVE LOGITS
     nep
    0.15
    369
    0.15
     Hind
    0.14
    ÙĦÛĮÙĦ
    0.14
    loyd
    0.14
     bread
    0.14
    reek
    0.14
    μμ
    0.14
    å§ĵ
    0.13
    cheng
    0.13
    Act Density 0.003%

    No Known Activations