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

    Neuronpedia

    INDEX
    Explanations

    negative or restrictive expressions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OVE
    -0.17
    ắn
    -0.15
    алÑĥ
    -0.15
    awns
    -0.14
    opers
    -0.14
    boy
    -0.14
    ubu
    -0.13
    ngr
    -0.13
     hereby
    -0.13
    itra
    -0.13
    POSITIVE LOGITS
     mind
    0.29
     dream
    0.28
    mind
    0.24
     Mind
    0.24
     Dream
    0.23
    Mind
    0.23
    Dream
    0.21
    梦
    0.21
     necessarily
    0.21
     wouldn
    0.20
    Act Density 0.086%

    No Known Activations