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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of a new world or a change in perspective

    oai_token-act-pair · gpt-3.5-turbo

    references to different worlds or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.99
    ifer
    -0.82
     actionGroup
    -0.81
    phabet
    -0.79
    oug
    -0.76
    sbm
    -0.76
    icer
    -0.74
    ++++
    -0.72
    odox
    -0.72
    etsk
    -0.71
    POSITIVE LOGITS
    building
    1.08
    liness
    1.05
    wide
    0.90
    scape
    0.89
    views
    0.78
    spawn
    0.78
     religions
    0.78
    fare
    0.77
    view
    0.77
    arium
    0.76
    Act Density 0.069%

    No Known Activations