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

    Neuronpedia

    INDEX
    Explanations

    instances of individuals or entities establishing their identity or reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ode
    -0.16
    bild
    -0.15
    ildo
    -0.14
    ernels
    -0.14
    ÑĮÑİÑĤ
    -0.14
    orum
    -0.14
     thiên
    -0.13
    ERVER
    -0.13
    aniu
    -0.13
    mostat
    -0.13
    POSITIVE LOGITS
     themselves
    0.71
     itself
    0.71
     himself
    0.66
     herself
    0.66
     ourselves
    0.55
     Himself
    0.52
     yourself
    0.52
     oneself
    0.51
     siÄĻ
    0.49
     zich
    0.48
    Act Density 0.173%

    No Known Activations