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

    Neuronpedia

    INDEX
    Explanations

    exact phrases or descriptions that denote precision and correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.70
     <<<<<<<<<<<<<<
    -0.69
     autorytatywna
    -0.66
    ThroughAttribute
    -0.65
    }))
    -0.63
    ssil
    -0.63
     henvisninger
    -0.61
    gameserver
    -0.60
    }\]
    -0.59
     commonly
    -0.58
    POSITIVE LOGITS
     exactly
    0.74
     Exactly
    0.70
     precisely
    0.69
     EXACTLY
    0.68
    exactly
    0.67
     exac
    0.65
    Perfectly
    0.64
    Exactly
    0.62
     esattamente
    0.61
     genau
    0.61
    Act Density 0.138%

    No Known Activations