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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consumer behavior or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ossal
    -0.15
    .dtd
    -0.15
     опÑĢеделен
    -0.14
     teg
    -0.14
    aign
    -0.14
    iqueta
    -0.14
     øns
    -0.14
     nghiêm
    -0.14
    leyen
    -0.14
    ectl
    -0.13
    POSITIVE LOGITS
     flock
    0.29
     beginning
    0.27
     increasingly
    0.27
     becoming
    0.25
     waking
    0.22
     finding
    0.21
     starting
    0.21
     being
    0.20
     discovering
    0.20
     turning
    0.20
    Act Density 0.130%

    No Known Activations