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

    Neuronpedia

    INDEX
    Explanations

    words related to group membership or ownership

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to belonging and community membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebels
    -0.81
    iatus
    -0.76
     Hydra
    -0.74
     Prometheus
    -0.72
     Alchemist
    -0.68
     Tarant
    -0.67
     Rampage
    -0.66
     Bulgarian
    -0.65
     Hercules
    -0.65
     cooldown
    -0.65
    POSITIVE LOGITS
    ahime
    0.78
    ãĤ©
    0.77
    ãĤ§
    0.76
    uable
    0.75
    PsyNetMessage
    0.72
    uty
    0.70
    00200000
    0.68
    agos
    0.67
    utive
    0.65
    ovan
    0.65
    Act Density 0.000%

    No Known Activations