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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "explore" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongs
    -0.16
    letes
    -0.16
    allis
    -0.16
    iddles
    -0.15
    comings
    -0.15
     ÑĢÑĥк
    -0.15
    leness
    -0.15
    erness
    -0.15
    leted
    -0.15
    quired
    -0.15
    POSITIVE LOGITS
    ainer
    0.31
    oring
    0.27
    oration
    0.27
    aining
    0.27
    ained
    0.25
    AINER
    0.23
    ainers
    0.23
    oded
    0.23
    ains
    0.23
    ode
    0.23
    Act Density 0.004%

    No Known Activations