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

    Neuronpedia

    INDEX
    Explanations

    names of technical software tools or platforms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    -+-+
    -0.81
    pees
    -0.80
    verbs
    -0.77
    NetMessage
    -0.76
    cedes
    -0.76
    umenthal
    -0.76
    uria
    -0.76
    requires
    -0.75
    ourning
    -0.74
    thia
    -0.74
    POSITIVE LOGITS
     logo
    1.16
     universe
    1.09
     Foundation
    1.06
     playbook
    1.05
     fanbase
    1.03
     debacle
    1.03
     saga
    1.03
     lineup
    1.01
     bandwagon
    1.00
     team
    0.98
    Act Density 0.346%

    No Known Activations