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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supposedly
    -0.17
    acho
    -0.16
    zk
    -0.15
     hopefully
    -0.14
    _ie
    -0.14
     presumably
    -0.13
    itol
    -0.13
    fi
    -0.13
    hopefully
    -0.13
    apper
    -0.13
    POSITIVE LOGITS
     to
    0.41
     να
    0.20
    to
    0.18
    	to
    0.18
    sto
    0.17
    toBe
    0.17
     avoir
    0.17
    antly
    0.16
    togroup
    0.16
    _to
    0.16
    Act Density 0.053%

    No Known Activations