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

    Neuronpedia

    INDEX
    Explanations

    expressions of commitment and assurances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     El
    -0.45
    у
    -0.44
    面
    -0.43
    elf
    -0.43
    คว
    -0.43
    El
    -0.40
    GO
    -0.39
    Herr
    -0.38
     may
    -0.38
    zeg
    -0.37
    POSITIVE LOGITS
     Roskov
    0.88
    esserung
    0.84
     avoient
    0.83
     vectorielles
    0.83
     NSCoder
    0.82
     étoient
    0.82
     purpoſe
    0.81
     feroit
    0.81
     beginnetje
    0.80
    NUMX
    0.80
    Act Density 0.218%

    No Known Activations