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

    Neuronpedia

    INDEX
    Explanations

    words related to amplification and reinforcement of concepts or ideas, particularly in the context of their effects and impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.20
    urtles
    -0.15
    ukt
    -0.15
    rance
    -0.15
    exus
    -0.14
    ç¾
    -0.14
    aeper
    -0.14
    _EXPORT
    -0.13
    iro
    -0.13
    象
    -0.13
    POSITIVE LOGITS
    437
    0.16
    asi
    0.16
    ©
    0.16
    rax
    0.15
    /de
    0.15
    mlin
    0.15
    lej
    0.14
    /stretch
    0.14
    asure
    0.14
    ingleton
    0.13
    Act Density 0.041%

    No Known Activations