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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific numerical values or rankings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "ÂŃ" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IPM
    -0.64
     srfAttach
    -0.63
    éĹĺ
    -0.62
    ilts
    -0.61
    åį
    -0.61
     Emblem
    -0.60
    Reloaded
    -0.60
     Skull
    -0.59
     Ridley
    -0.59
     Monk
    -0.59
    POSITIVE LOGITS
    nesota
    0.75
    po
    0.74
    di
    0.74
    go
    0.72
    fect
    0.70
    ¿
    0.68
    spons
    0.68
    selves
    0.67
    gress
    0.67
    dra
    0.67
    Act Density 0.010%

    No Known Activations