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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence or presence of complications or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tantôt
    -0.65
     impractica
    -0.65
    seamnă
    -0.64
     saira
    -0.64
     invitamos
    -0.59
     hogyan
    -0.57
    SPATH
    -0.56
    numerusform
    -0.56
     lingue
    -0.55
     Coronel
    -0.55
    POSITIVE LOGITS
     whatsoever
    0.95
     никаких
    0.93
     keinerlei
    0.85
     nada
    0.82
     Signalez
    0.80
     никакого
    0.80
     nothing
    0.78
     none
    0.77
     no
    0.76
    没有任何
    0.76
    Act Density 0.699%

    No Known Activations