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

    Neuronpedia

    INDEX
    Explanations

    words related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.89
    VIAF
    -0.88
    AnchorStyles
    -0.86
     Rhino
    -0.85
     Osp
    -0.85
     Mezz
    -0.84
    SequentialGroup
    -0.84
     newOwner
    -0.83
    ✨:
    -0.82
     curfew
    -0.82
    POSITIVE LOGITS
     action
    2.44
     actions
    2.29
     Action
    2.25
    Action
    2.13
     Actions
    2.11
     ACTION
    2.09
    Actions
    2.06
    action
    2.02
    actions
    1.93
     ACTIONS
    1.85
    Act Density 0.086%

    No Known Activations