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

    Neuronpedia

    INDEX
    Explanations

    examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of "examples" or "examples of" along with their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wig
    -0.68
    houses
    -0.68
    urance
    -0.66
    ower
    -0.66
    ement
    -0.64
    ements
    -0.64
    EMENT
    -0.61
    umb
    -0.60
    ester
    -0.60
    aintain
    -0.59
    POSITIVE LOGITS
    acan
    0.72
     heroism
    0.72
     guiActiveUnfocused
    0.69
    £ı
    0.67
    natureconservancy
    0.65
     illustrating
    0.65
    imov
    0.65
     Valid
    0.64
    akeru
    0.64
     demonstrating
    0.64
    Act Density 0.101%

    No Known Activations