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

    Neuronpedia

    INDEX
    Explanations

    words related to abandonment and withdrawal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ";}
    -0.89
    "]}
    -0.85
     Deniz
    -0.85
     Vesu
    -0.83
    ();*/
    -0.82
    $.}
    -0.82
     CIT
    -0.82
    principalTable
    -0.82
     }\
    -0.80
     }(\
    -0.80
    POSITIVE LOGITS
     Ab
    1.65
     ab
    1.52
     AB
    1.45
    Ab
    1.37
    ab
    1.12
     ablation
    1.07
     Abigail
    1.06
     Abbott
    1.05
     abzu
    1.05
     Abram
    1.03
    Act Density 0.104%

    No Known Activations