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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe perceptions of appearance or reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hacks
    -0.15
    agar
    -0.15
    xp
    -0.15
    iye
    -0.15
    çķ
    -0.14
    hell
    -0.14
    ollen
    -0.14
    士
    -0.14
     souls
    -0.13
    quam
    -0.13
    POSITIVE LOGITS
    igt
    0.16
    erne
    0.15
     dur
    0.15
    SETS
    0.14
     Lesser
    0.14
    marsh
    0.14
    -toggler
    0.14
    ált
    0.14
    onga
    0.14
    åĻ
    0.13
    Act Density 0.286%

    No Known Activations