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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vá
    -0.15
    emer
    -0.14
    ener
    -0.14
    abay
    -0.14
    akah
    -0.14
     useClass
    -0.14
    ieur
    -0.14
    utterstock
    -0.14
    omers
    -0.14
    undy
    -0.13
    POSITIVE LOGITS
     anything
    0.32
     anyone
    0.30
     anybody
    0.28
     nothing
    0.27
    anything
    0.24
     memory
    0.24
    nothing
    0.23
     Anyone
    0.23
     Anything
    0.23
    Anyone
    0.22
    Act Density 0.072%

    No Known Activations