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

    Neuronpedia

    INDEX
    Explanations

    references to supernatural or mythical creatures in tense situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sponge
    -0.16
     cust
    -0.15
     Birds
    -0.15
     Hamm
    -0.15
    vant
    -0.15
    üz
    -0.15
    viso
    -0.14
    wart
    -0.14
    egg
    -0.14
    acts
    -0.14
    POSITIVE LOGITS
     wer
    0.37
    Wer
    0.36
     Shift
    0.36
    Shift
    0.35
     shift
    0.35
     Wer
    0.34
    shift
    0.34
     wol
    0.33
    -shift
    0.32
     shifted
    0.31
    Act Density 0.106%

    No Known Activations