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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the general status or condition of things/events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express change or the state of affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lication
    -0.76
    pora
    -0.75
    Joined
    -0.69
    lees
    -0.69
    obook
    -0.68
    nor
    -0.66
     descriptor
    -0.65
    ELD
    -0.63
    ledge
    -0.62
    odied
    -0.62
    POSITIVE LOGITS
     downhill
    0.98
     spir
    0.88
     unravel
    0.76
     escalated
    0.76
     unfolded
    0.75
     smoothly
    0.74
     transpired
    0.74
    MpServer
    0.72
     Spiral
    0.71
     cov
    0.71
    Act Density 0.196%

    No Known Activations