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

    Neuronpedia

    INDEX
    Explanations

    the word "helping to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the purpose or intention of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Notting
    -0.67
     Canary
    -0.66
     Sparrow
    -0.65
    ModLoader
    -0.64
     Goth
    -0.64
     faults
    -0.63
     Procedure
    -0.62
     POV
    -0.61
     Ferr
    -0.61
     Spaces
    -0.60
    POSITIVE LOGITS
     strengthen
    1.25
     alleviate
    1.24
     establish
    1.24
     relieve
    1.20
     amplify
    1.17
     promote
    1.16
     clarify
    1.16
     organize
    1.16
     facilitate
    1.16
     create
    1.15
    Act Density 0.086%

    No Known Activations