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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or commentary on interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ><?
    -0.16
    ñana
    -0.16
     CLICK
    -0.15
    ataka
    -0.14
     Click
    -0.14
    hiba
    -0.14
    ertino
    -0.14
     Worlds
    -0.13
     click
    -0.13
    CLICK
    -0.13
    POSITIVE LOGITS
     EDIT
    0.17
    EDIT
    0.16
     also
    0.16
     hence
    0.16
     edit
    0.15
     ultimately
    0.15
     otherwise
    0.15
    Edit
    0.15
     Edit
    0.15
     ALSO
    0.15
    Act Density 0.423%

    No Known Activations