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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "left" in various contexts, often suggesting abandonment or lack of options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.72
    rium
    -0.67
    Temperature
    -0.66
     srfAttach
    -0.63
    wcsstore
    -0.62
    NT
    -0.61
    issance
    -0.60
     mesh
    -0.60
    antz
    -0.60
    atsuki
    -0.60
    POSITIVE LOGITS
    overs
    1.11
     untreated
    1.05
     behind
    0.99
     undone
    0.96
     intact
    0.85
     untouched
    0.84
     unprotected
    0.83
     wondering
    0.83
    wing
    0.83
     alive
    0.81
    Act Density 0.011%

    No Known Activations