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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating contact or making inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.65
    ########.
    -0.65
    OSD
    -0.63
    tagext
    -0.60
     zood
    -0.59
    COUVER
    -0.59
    verwijspagina
    -0.58
    istoitu
    -0.57
     KIA
    -0.57
     MIA
    -0.56
    POSITIVE LOGITS
    WarningLevel
    0.59
     him
    0.59
     them
    0.57
     this
    0.57
     henne
    0.54
     us
    0.52
     the
    0.51
     setia
    0.51
     fiducia
    0.50
     sesama
    0.49
    Act Density 0.276%

    No Known Activations