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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahoma
    -0.15
    rought
    -0.15
    å°İ
    -0.15
     y
    -0.14
    786
    -0.14
     اÙĦÙĤرÙĨ
    -0.14
     Circ
    -0.14
    133
    -0.14
    adow
    -0.13
     Engine
    -0.13
    POSITIVE LOGITS
    aptops
    0.16
    γοÏħ
    0.16
    pector
    0.15
    Hooks
    0.15
    abcdefghijklmnop
    0.14
    antan
    0.14
    unding
    0.14
     Tân
    0.14
    ihan
    0.14
    imetype
    0.14
    Act Density 0.017%

    No Known Activations