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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions that are taken towards a specific goal or result

    oai_token-act-pair · gpt-3.5-turbo

    actions associated with maintenance, support, and production processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phi
    -0.74
     Horton
    -0.67
     Cah
    -0.66
     Suffolk
    -0.65
    chu
    -0.60
     CFR
    -0.60
     Dracula
    -0.59
    guyen
    -0.59
     Sina
    -0.59
     Ars
    -0.58
    POSITIVE LOGITS
     separately
    0.91
     anytime
    0.90
    quished
    0.88
     individually
    0.83
     by
    0.82
     statically
    0.82
     cheaply
    0.82
    ividually
    0.79
     securely
    0.79
     offline
    0.78
    Act Density 0.282%

    No Known Activations