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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.17
    hed
    -0.16
    igner
    -0.15
    amin
    -0.15
     themselves
    -0.15
    sson
    -0.15
    SSIP
    -0.15
    ernote
    -0.14
    nd
    -0.14
    bond
    -0.14
    POSITIVE LOGITS
    oyer
    0.17
    ائÙĦ
    0.15
    *)_
    0.14
    pike
    0.14
     coh
    0.14
    isy
    0.14
    sense
    0.14
    á»Ńa
    0.14
     tslib
    0.14
    /us
    0.13
    Act Density 0.025%

    No Known Activations