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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating uncertainty or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥĥãĤ¯
    -0.16
    argas
    -0.16
    tuÄŁ
    -0.14
    antro
    -0.14
    -regexp
    -0.14
    HasBeen
    -0.13
    cctor
    -0.13
    oice
    -0.13
    iflower
    -0.13
    undler
    -0.13
    POSITIVE LOGITS
     going
    0.67
     gonna
    0.66
    going
    0.51
    gon
    0.47
     Going
    0.45
     gon
    0.44
    Going
    0.41
    -going
    0.41
     bound
    0.32
     gun
    0.32
    Act Density 0.182%

    No Known Activations