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

    Neuronpedia

    INDEX
    Explanations

    phrases related to electronic devices with a physical component

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to storytelling and narrative structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PF
    -0.73
    merce
    -0.70
    SEA
    -0.70
    terms
    -0.69
    Specific
    -0.68
    MON
    -0.67
    ophen
    -0.66
    idential
    -0.65
    vic
    -0.65
    Plot
    -0.65
    POSITIVE LOGITS
     forth
    0.81
     Tide
    0.72
    arching
    0.71
    puff
    0.69
     crawl
    0.65
    enment
    0.64
     sofa
    0.63
     throat
    0.61
    erers
    0.61
     heels
    0.60
    Act Density 0.116%

    No Known Activations