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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or entities

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the letter 'v' and the presence of notable names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.76
     censored
    -0.76
     destro
    -0.71
     decay
    -0.68
     dracon
    -0.67
     entangled
    -0.63
     spoiled
    -0.63
     deprivation
    -0.62
     seeker
    -0.61
     hardened
    -0.61
    POSITIVE LOGITS
    ü
    1.10
    idd
    1.08
    ä
    1.01
    aja
    1.01
    ij
    0.99
    urd
    0.98
    ani
    0.97
    itz
    0.94
    reet
    0.94
    anski
    0.94
    Act Density 0.174%

    No Known Activations