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

    Neuronpedia

    INDEX
    Explanations

    references to "words" and their usage in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     becauſe
    -0.72
     zelve
    -0.72
    sphase
    -0.71
    aughter
    -0.70
     pleaſure
    -0.67
     Initialise
    -0.66
    первых
    -0.65
     rospy
    -0.65
    RegistryLite
    -0.65
     dieux
    -0.64
    POSITIVE LOGITS
     Wink
    0.65
    vers
    0.58
    ers
    0.57
    ψ
    0.55
    bote
    0.54
    0.54
     kali
    0.53
     esper
    0.53
    mata
    0.53
     Omega
    0.53
    Act Density 0.004%

    No Known Activations