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

    Neuronpedia

    INDEX
    Explanations

    verbs related to demonstrating or displaying actions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to demonstrating evidence or proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ksh
    -0.79
     Topic
    -0.74
     indefinitely
    -0.69
    inqu
    -0.68
    levard
    -0.66
     sugg
    -0.65
    ardi
    -0.64
    Var
    -0.61
    chn
    -0.61
    apter
    -0.60
    POSITIVE LOGITS
     signs
    1.06
     willingness
    1.04
     mercy
    1.01
     resemblance
    0.96
     kindness
    0.94
     resilience
    0.92
     prowess
    0.92
     appreciation
    0.90
     remorse
    0.90
     restraint
    0.89
    Act Density 0.149%

    No Known Activations