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

    Neuronpedia

    INDEX
    Explanations

    phrases related to food, cleaning, and chemical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tilt
    -0.16
    redd
    -0.15
    enk
    -0.14
     pitch
    -0.14
     outputs
    -0.14
    pitch
    -0.14
     Tos
    -0.14
    νή
    -0.14
     opaque
    -0.14
    lash
    -0.14
    POSITIVE LOGITS
     Kontakt
    0.21
     diffusion
    0.20
    æ¸
    0.20
     contacto
    0.19
     contact
    0.19
    -contact
    0.19
     Diff
    0.19
     конÑĤак
    0.19
    contact
    0.18
     contacting
    0.18
    Act Density 0.083%

    No Known Activations