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

    Neuronpedia

    INDEX
    Explanations

    terms related to escalating levels or increases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flav
    -0.53
     BorderRadius
    -0.52
    assertj
    -0.51
     CONT
    -0.51
     PUBL
    -0.50
     StringTokenizer
    -0.48
    contentPadding
    -0.48
    Flav
    -0.48
    assertIs
    -0.47
     Payload
    -0.47
    POSITIVE LOGITS
     increase
    0.89
    Increase
    0.89
     Increase
    0.88
    increase
    0.82
     INCREASE
    0.73
    decrease
    0.73
     increased
    0.71
     zvý
    0.71
     Erhöhung
    0.70
    Decrease
    0.69
    Act Density 0.299%

    No Known Activations