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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases that indicate the existence and conditions of a subject's rights or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     freaking
    -0.61
     kinda
    -0.57
     udah
    -0.56
     freaked
    -0.56
     sneaky
    -0.54
    CharStream
    -0.51
     freakin
    -0.51
    umenti
    -0.50
     pissed
    -0.50
    GenerationType
    -0.49
    POSITIVE LOGITS
     nevertheless
    0.72
     doubtless
    0.71
     demikian
    0.68
     meanwhile
    0.66
     дописавши
    0.66
     Meksiku
    0.65
     manifestly
    0.64
     således
    0.63
     thus
    0.63
     moreover
    0.63
    Act Density 0.737%

    No Known Activations