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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe negative qualities or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    079
    -0.14
    formance
    -0.14
    digit
    -0.14
     célib
    -0.14
    aint
    -0.14
     immature
    -0.13
    iteration
    -0.13
    ucu
    -0.13
    nodoc
    -0.13
     Mature
    -0.13
    POSITIVE LOGITS
    rik
    0.17
    ummies
    0.15
     Wallace
    0.15
    gem
    0.14
    rál
    0.14
    iscal
    0.14
    ROTO
    0.14
    beeld
    0.14
    eken
    0.14
    æµľ
    0.14
    Act Density 0.046%

    No Known Activations